© 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. 38192
    Prev
    Next
    INDEX
    Explanations

    hard money

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

    constant velocity/speed

    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
    ளி
    0.46
    راهيم
    0.45
    埄
    0.45
    த்திற்கு
    0.44
    ]/*
    0.44
    作为
    0.44
    باً
    0.44
    يهم
    0.44
    ро
    0.44
    ിക്കുന്ന
    0.44
    POSITIVE LOGITS
     آموزش
    0.57
     ဟ
    0.53
     دی
    0.51
     جدید
    0.50
     ܕ
    0.50
     DOS
    0.50
     кораб
    0.49
     DOL
    0.49
     دوم
    0.47
     호텔
    0.47
    Activations Density 0.000%

    No Known Activations