© 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. 22-GEMMASCOPE-RES-131K
    7. 25559
    Prev
    Next
    INDEX
    Explanations

    much

    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_22/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
    -2.09
    もうすぐ
    -2.06
    場合には
    -1.91
    の詳細
    -1.88
     jugar
    -1.86
    깽
    -1.85
    corrhi
    -1.84
     wzglę
    -1.77
    𓈒
    -1.76
    つづく
    -1.74
    POSITIVE LOGITS
    を
    2.20
    n
    1.87
    w
    1.86
    m
    1.72
    但却
    1.71
    p
    1.67
    ,
    1.64
    d
    1.59
    かもしれませんが
    1.57
    が
    1.50
    Activations Density 0.017%

    No Known Activations