© 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. 33454
    Prev
    Next
    INDEX
    Explanations

    numbers and units

    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
     the
    -2.08
    おわりに
    -1.74
     a
    -1.73
    O
    -1.65
    and
    -1.59
    i
    -1.57
    So
    -1.55
     teh
    -1.52
    うわ
    -1.52
    どれだけ
    -1.46
    POSITIVE LOGITS
    ジナル
    1.79
    咈
    1.55
     Anſ
    1.43
    髕
    1.43
     contextLoads
    1.38
    方針
    1.36
    macar
    1.36
    ネート
    1.35
    quels
    1.34
     consé
    1.33
    Activations Density 0.052%

    No Known Activations