© 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. 32106
    Prev
    Next
    INDEX
    Explanations

    documentation tags like @property

    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
    <0xF4>
    -0.98
    Lett
    -0.96
    ⁕
    -0.96
    –
    -0.94
     lesson
    -0.93
     Trains
    -0.89
    РЫ
    -0.89
    Camp
    -0.86
    Ident
    -0.86
     cocina
    -0.85
    POSITIVE LOGITS
     @
    2.19
    @
    1.48
    理由は
    0.93
    restaurante
    0.89
    就是一个
    0.88
     llamaba
    0.85
     dispone
    0.84
    밭
    0.84
    ,@
    0.84
     produjo
    0.82
    Activations Density 0.002%

    No Known Activations