© 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. 244187
    Prev
    Next
    INDEX
    Explanations

    TV series or purchase

    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
    а
    0.65
    E
    0.63
    ל
    0.57
    "
    0.57
    е
    0.56
    Э
    0.55
    Ex
    0.54
    ни
    0.54
    An
    0.53
    Imagine
    0.53
    POSITIVE LOGITS
     사고
    0.55
    asciiPanel
    0.49
     respiratoires
    0.45
    sadpoetry
    0.45
    icycles
    0.45
    ձ
    0.45
     मज़
    0.45
    ța
    0.44
    لیفون
    0.44
     池
    0.44
    Activations Density 0.000%

    No Known Activations