© 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. 71292
    Prev
    Next
    INDEX
    Explanations

    Conversely, It, If

    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
     and
    -1.53
     После
    -1.52
    n
    -1.48
     ""),
    -1.47
     نیز
    -1.46
    raisemb
    -1.45
     "";
    -1.44
     from
    -1.43
    發生
    -1.41
    +"\
    -1.41
    POSITIVE LOGITS
    秾
    1.83
    棐
    1.74
     pochi
    1.66
     it
    1.64
    ’
    1.63
    ჱ
    1.62
    殽
    1.59
     you
    1.57
    籥
    1.55
    この
    1.53
    Activations Density 0.012%

    No Known Activations