© 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. 211424
    Prev
    Next
    INDEX
    Explanations

    candidates short-listed

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

    explanation and inheritance

    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
    textFile
    0.46
    ap
    0.46
     disag
    0.45
    uix
    0.45
    iatrics
    0.44
    ➌
    0.44
     sén
    0.44
     Exchequer
    0.43
    ➁
    0.43
    ont
    0.43
    POSITIVE LOGITS
    е
    0.48
     serán
    0.43
    ева
    0.43
    ມັນ
    0.42
     வட்ட
    0.40
    возможно
    0.40
     fervent
    0.40
    কাল
    0.40
    ப்பெ
    0.40
     Rainier
    0.40
    Activations Density 0.000%

    No Known Activations