© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 60493
    Prev
    Next
    INDEX
    Explanations

    starts with `pub`, `use`, `fn`, `mod`, `Q`, `Live`, `In`, `FAQ`

    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
    ásticas
    -0.84
    Хочу
    -0.81
    rogates
    -0.77
    璽
    -0.77
    ális
    -0.77
    وارض
    -0.77
    classify
    -0.75
    ーチ
    -0.75
     उत्पाद
    -0.75
    貔
    -0.73
    POSITIVE LOGITS
     use
    2.23
    use
    1.84
    pub
    1.81
     pub
    1.69
     USE
    1.42
     Use
    1.34
    Use
    1.34
    USE
    1.25
     Pub
    1.18
     mod
    1.17
    Activations Density 0.019%

    No Known Activations