© 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. 182313
    Prev
    Next
    INDEX
    Explanations

    AMAZINGstunningbestnow

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

    dismantle, podagra, forces

    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
     बतौर
    0.46
    setPrototypeOf
    0.46
    amasını
    0.45
     அம்ச
    0.44
    czas
    0.43
    uiscono
    0.42
     겸
    0.42
    стю
    0.42
    煂
    0.42
    Crisis
    0.41
    POSITIVE LOGITS
    }}-\
    0.53
     gutt
    0.53
     Россия
    0.50
     jaka
    0.48
     ゆっくり
    0.48
     ice
    0.47
     exced
    0.46
     conda
    0.46
     hym
    0.46
     ging
    0.45
    Activations Density 0.000%

    No Known Activations