© 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. 16253
    Prev
    Next
    INDEX
    Explanations

    return false

    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
     also
    -1.22
    м
    -0.95
    TBA
    -0.93
     география
    -0.92
    也要
    -0.90
     Ministero
    -0.86
     også
    -0.85
     vairāk
    -0.84
    ycznie
    -0.84
     также
    -0.83
    POSITIVE LOGITS
    Нет
    1.13
     nothing
    1.13
     none
    1.12
    不到
    1.08
     no
    1.08
    Etimo
    1.05
     zero
    1.05
    ไม่มี
    1.03
     nope
    1.03
     or
    1.02
    Activations Density 0.014%

    No Known Activations