© 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. 154232
    Prev
    Next
    INDEX
    Explanations

    preferred providers

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

    online store

    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
    सारा
    0.47
    rup
    0.46
    ᅨ
    0.46
    endale
    0.44
    ாளையம்
    0.44
    俦
    0.42
    caster
    0.41
    seleccion
    0.41
     Weinberg
    0.41
     disparition
    0.41
    POSITIVE LOGITS
    查询
    0.49
    壷
    0.47
    フト
    0.46
    填充
    0.46
     অনুরোধ
    0.46
    ப்பு
    0.45
     তুম
    0.45
     Akadem
    0.45
    ̉i
    0.44
    {}'.
    0.44
    Activations Density 0.000%

    No Known Activations