© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 117511
    Prev
    Next
    INDEX
    Explanations

    school types, disease types, weapon types, experiment types

    np_acts-logits-general · gemini-2.5-flash-lite

    descriptions of institutional or scientific classifications with multiple attributes.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron fires on descriptive modifiers—especially compound or category‐defining adjectives and nouns (e.g. “private,” “educational,” “Catholic,” “co-educational,” “two-component,” “hard court”) that qualify or classify the main noun.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    為に
    -1.52
    マジで
    -1.38
    ようになって
    -1.35
    凄く
    -1.33
    感じで
    -1.31
    ことは
    -1.30
    んですよ
    -1.30
    新しく
    -1.29
    ときは
    -1.28
    場所で
    -1.27
    POSITIVE LOGITS
    <bos>
    1.63
    しかも
    1.38
    その
    1.37
    を
    1.29
    もちゃ
    1.29
    дован
    1.23
    などが
    1.21
     мои
    1.16
    もしろ
    1.14
    且
    1.14
    Activations Density 0.687%

    No Known Activations