© 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. 34-GEMMASCOPE-RES-131K
    7. 63939
    Prev
    Next
    INDEX
    Explanations

    possibility or recurrence

    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_34/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
    っており
    -1.16
     instagram
    -1.09
     actualmente
    -1.09
     oldukça
    -1.08
     extrêmement
    -1.06
    めちゃくちゃ
    -1.05
    constexpr
    -1.04
     Instagram
    -1.04
     recomiendo
    -1.03
     عددی
    -1.03
    POSITIVE LOGITS
     again
    1.25
     perhaps
    1.24
    ⅖
    1.09
     someday
    1.07
     rozpoczę
    1.06
     somehow
    1.06
    ❣
    1.06
     sfida
    1.05
    ⅗
    1.04
    ridescent
    1.03
    Activations Density 0.111%

    No Known Activations