© 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-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 8678
    Prev
    Next
    INDEX
    Explanations

    normalization of harmful behavior

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_16k_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
    िलासपुर
    1.12
     బ్యాంకు
    1.03
     전기
    1.01
    乂
    1.00
    ARIFF
    0.96
    ົ້າ
    0.96
     بعنوان
    0.96
     請
    0.95
    geoType
    0.94
     노동
    0.93
    POSITIVE LOGITS
    出来
    0.65
    de
    0.64
    ந்துக
    0.62
    study
    0.61
    maybe
    0.61
    Sadly
    0.60
     شاید
    0.60
    ider
    0.59
    deg
    0.59
    ide
    0.58
    Activations Density 0.414%

    No Known Activations