© 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. 2033
    Prev
    Next
    INDEX
    Explanations

    listing and conjunction

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

    translate, summarize, documentation, debugging, troubleshooting

    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
    ЛИ
    0.49
    孱
    0.46
    נ
    0.46
    तिहासिक
    0.46
    ЛЕ
    0.44
    숫
    0.43
     интегри
    0.42
    矜
    0.42
    ̙
    0.42
     μεγά
    0.41
    POSITIVE LOGITS
     też
    0.69
     inoltre
    0.66
     và
    0.62
     نیز
    0.58
     மற்றும்
    0.57
     también
    0.56
     valamint
    0.55
     and
    0.55
     also
    0.54
     tampoco
    0.54
    Activations Density 0.104%

    No Known Activations