© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43835
    Prev
    Next
    INDEX
    Explanations

    common phrases and continuations

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

    The neuron responds to content words (nouns, verbs, adjectives, etc.) rather than to common function words or punctuation.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     also
    -1.82
     également
    -1.69
     with
    -1.46
    躂
    -1.43
     também
    -1.41
     también
    -1.38
    </h2>
    -1.38
    Լ
    -1.26
     ‘’
    -1.23
     contactez
    -1.23
    POSITIVE LOGITS
     those
    1.43
     They
    1.37
     هایی
    1.28
     like
    1.28
     that
    1.27
    iniums
    1.25
    下車
    1.23
    Their
    1.23
    leigh
    1.23
    ✑
    1.20
    Activations Density 0.053%

    No Known Activations