© 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-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 3651
    Prev
    Next
    INDEX
    Explanations

    normalization of harmful speech and behavior

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    t
    1.09
    d
    0.92
    nem
    0.83
    g
    0.82
    lük
    0.82
    lots
    0.80
    لي
    0.77
    -
    0.77
     (
    0.76
    normal
    0.75
    POSITIVE LOGITS
     normalized
    1.16
     normalization
    1.11
     normalised
    1.05
     normalizing
    1.03
     Normalize
    1.03
     normalize
    1.01
    ط
    0.96
    zione
    0.93
    normalize
    0.89
     Normalized
    0.86
    Activations Density 0.013%

    No Known Activations