© 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. 211325
    Prev
    Next
    INDEX
    Explanations

    version of, will take

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

    frequent extreme weather

    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
    ++;
    0.46
    Становништво
    0.46
    يء
    0.45
    ++
    0.44
     pronunci
    0.44
    在
    0.44
     modestly
    0.44
    蜂
    0.43
    𝟏
    0.43
     byte
    0.42
    POSITIVE LOGITS
     gäller
    0.52
     prête
    0.47
     pyl
    0.46
    ada
    0.46
     créd
    0.46
     догово
    0.45
    தைய
    0.45
    ਲੇ
    0.44
     alluring
    0.44
     estábamos
    0.43
    Activations Density 0.000%

    No Known Activations