© 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. 175355
    Prev
    Next
    INDEX
    Explanations

    nature of, allies when, find additional

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

    physical properties and conditions

    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
    ᅣ
    0.51
    アン
    0.48
    总之
    0.47
    Bri
    0.44
    LONG
    0.43
     सत्तार
    0.43
    基
    0.43
    還
    0.43
     Schen
    0.42
    紘
    0.42
    POSITIVE LOGITS
     peels
    0.57
     booths
    0.55
     blemishes
    0.55
     leverages
    0.52
     nostrils
    0.50
     critters
    0.50
     voltages
    0.50
     xổ
    0.49
     imbalances
    0.49
     Representatives
    0.48
    Activations Density 0.000%

    No Known Activations