© 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. 130140
    Prev
    Next
    INDEX
    Explanations

    how could you

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    茳
    -1.70
     vermelha
    -1.63
    ruguay
    -1.63
    歲
    -1.58
    ));
    -1.57
    ,:]
    -1.54
    toFloat
    -1.44
    getTeam
    -1.44
    قامت
    -1.43
    咘
    -1.43
    POSITIVE LOGITS
    </h2>
    1.58
    0
    1.55
     of
    1.51
    q
    1.45
     <
    1.43
     \
    1.41
    ~
    1.41
    ing
    1.41
     ~
    1.38
     Of
    1.34
    Activations Density 0.008%

    No Known Activations