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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 10828
    Prev
    Next
    INDEX
    Explanations

    treatment and development

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

    medical or scientific contexts related to treatments, development, or presence of conditions.

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

    The neuron flags abstract, high‐level action nouns or nominalized verbs (e.g. development, inhibition, treatment, use, presence) that describe processes or study objectives.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     only
    -1.33
     continuing
    -1.33
    フォーマ
    -1.30
     there
    -1.30
    .......
    -1.23
    もしか
    -1.23
    がありますが
    -1.23
    アプリケーション
    -1.21
    って思
    -1.21
     other
    -1.21
    POSITIVE LOGITS
     of
    4.63
    ためには
    1.87
    場合には
    1.57
     menyen
    1.47
    為に
    1.45
     Perang
    1.41
     geschenk
    1.39
     hunne
    1.38
    ことも
    1.34
     viena
    1.33
    Activations Density 0.144%

    No Known Activations