© 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. 249083
    Prev
    Next
    INDEX
    Explanations

    registered, calculate, demand

    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
     curr
    0.55
     FTA
    0.46
     statesman
    0.46
     src
    0.46
     instantaneous
    0.45
     understatement
    0.45
    q
    0.45
     TEXT
    0.45
    ̀m
    0.45
     luxury
    0.45
    POSITIVE LOGITS
     Elimin
    0.54
    دف
    0.50
    漣
    0.49
    丏
    0.49
    benar
    0.48
     автомобиль
    0.48
    להקה
    0.48
    秕
    0.48
    槤
    0.47
     конкурса
    0.47
    Activations Density 0.000%

    No Known Activations