© 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. 99322
    Prev
    Next
    INDEX
    Explanations

    APS, Lyn, Pow, Wha, FET, зада

    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
    ).
    -3.44
    ve
    -3.05
    ’,
    -3.03
    le
    -2.92
     exceptionally
    -2.91
    and
    -2.84
    ’.
    -2.77
    聍
    -2.70
     ess
    -2.64
     последних
    -2.61
    POSITIVE LOGITS
     bedenken
    2.58
    ↵↵
    2.45
     hendak
    2.42
     berharap
    2.41
    镦
    2.33
    夲
    2.31
    缯
    2.31
     If
    2.30
     думал
    2.25
    孭
    2.25
    Activations Density 0.036%

    No Known Activations