© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 141990
    Prev
    Next
    INDEX
    Explanations

    prepare to download

    np_acts-logits-general · gemini-2.5-flash-lite

    process investigation or planning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ी
    0.47
    逼
    0.47
    示す
    0.46
     باپ
    0.46
    editar
    0.45
    䄱
    0.44
    estima
    0.43
    смо
    0.43
    тари
    0.42
     بہت
    0.42
    POSITIVE LOGITS
     Gears
    0.52
     Buick
    0.51
     Compressor
    0.48
    在我们
    0.48
    Accelerometer
    0.47
    ⅜
    0.46
     Normalize
    0.45
     Antibodies
    0.45
    Borderless
    0.44
     Anosov
    0.44
    Activations Density 0.001%

    No Known Activations