© 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. 78968
    Prev
    Next
    INDEX
    Explanations

    terminate or discontinue

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

    explaining difficult concepts

    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
     Москва
    0.49
    九
    0.48
    ۳
    0.48
    歡
    0.47
     ঢাকায়
    0.45
     পার্বত্য
    0.45
     ಬೆಂಗಳ
    0.44
    ﻦ
    0.44
    гун
    0.42
    榔
    0.42
    POSITIVE LOGITS
     bleak
    0.48
     importa
    0.47
     exasper
    0.47
     signifikan
    0.46
    વો
    0.46
     murmur
    0.46
     deva
    0.45
     insignificant
    0.43
     வெறும்
    0.43
     vaše
    0.43
    Activations Density 0.004%

    No Known Activations