© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 98965
    Prev
    Next
    INDEX
    Explanations

    both and

    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
     réessayer
    -0.84
     DOMAIN
    -0.83
    為に
    -0.82
    ᥆
    -0.81
    Ещё
    -0.80
    向けの
    -0.80
    modelName
    -0.79
     pascal
    -0.79
    pila
    -0.79
     statesman
    -0.77
    POSITIVE LOGITS
     aspiring
    0.88
     superiore
    0.84
     also
    0.84
    wości
    0.83
    verte
    0.81
     various
    0.81
     городской
    0.79
    ğim
    0.79
     high
    0.78
     tako
    0.78
    Activations Density 0.000%

    No Known Activations