© 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. 193363
    Prev
    Next
    INDEX
    Explanations

    quality attributes or specific descriptions

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

    medical or technical terms

    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
    ‭
    0.45
    λεκ
    0.45
    urètre
    0.44
    olybdenum
    0.43
    メリカ
    0.43
    υχ
    0.43
    ^(
    0.42
    ፐ
    0.42
     моём
    0.41
    爸
    0.41
    POSITIVE LOGITS
     혁
    0.55
     routed
    0.50
     تست
    0.47
     که
    0.45
     ออก
    0.45
    rott
    0.44
     Routing
    0.44
     ട്ര
    0.43
     Routed
    0.43
     Fluss
    0.43
    Activations Density 0.001%

    No Known Activations