© 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. 34515
    Prev
    Next
    INDEX
    Explanations

    light and darkness

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

    I won't generate harmful content

    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
     اگه
    0.43
     ا
    0.42
     देखे
    0.41
     ﺍ
    0.41
     सबका
    0.40
     הא
    0.40
     अह
    0.40
     फटाफट
    0.40
    chenk
    0.40
    錨
    0.40
    POSITIVE LOGITS
     mayoría
    0.51
     cellulose
    0.49
     extraordinarily
    0.48
     supplemented
    0.47
    :'.
    0.46
     মস্ক
    0.45
     voluntarily
    0.44
     Cellulose
    0.44
     concealed
    0.43
    ヂ
    0.43
    Activations Density 0.000%

    No Known Activations