© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 113404
    Prev
    Next
    INDEX
    Explanations

    gently followed by action

    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
    {
    -3.06
    </strong>
    -2.44
    但我
    -2.20
     Then
    -2.14
     белая
    -2.14
     We
    -2.13
     “
    -2.13
    le
    -2.08
     act
    -2.08
    o
    -2.06
    POSITIVE LOGITS
    蟶
    2.91
    渽
    2.75
    埽
    2.63
     эту
    2.53
    नलोड
    2.38
     nhàng
    2.34
    鸶
    2.33
    )]
    2.28
    說
    2.28
    寕
    2.27
    Activations Density 0.009%

    No Known Activations