© 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. 184529
    Prev
    Next
    INDEX
    Explanations

    perfect square factors

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

    Gemini Pro, foreign characters, slurs

    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
     Nevada
    0.48
     }},
    0.47
     Beech
    0.47
     Франция
    0.46
    color
    0.46
     Colorado
    0.46
     traversed
    0.46
    filtered
    0.46
     অবিশ্বাস্য
    0.45
     Германия
    0.45
    POSITIVE LOGITS
    代言
    0.50
    廣告
    0.48
    社會
    0.47
    職
    0.46
    假期
    0.45
     abus
    0.45
    社会
    0.45
    🚨
    0.45
    你會
    0.45
    ؟
    0.44
    Activations Density 0.000%

    No Known Activations