© 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. 31-GEMMASCOPE-2-RES-262K
    7. 78685
    Prev
    Next
    INDEX
    Explanations

    worst atrocities, adapted to, comparing

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

    section headers or label phrases that end with a colon, often written in all caps or title case.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
    ཥ
    0.55
    权限
    0.49
     pestaña
    0.49
    鐐
    0.49
     voglia
    0.48
    CurrentByte
    0.48
    权力
    0.48
     быть
    0.47
    拶
    0.47
    阊
    0.47
    POSITIVE LOGITS
    ci
    0.50
    o
    0.49
    an
    0.46
    following
    0.46
    u
    0.45
    hire
    0.45
    op
    0.45
    per
    0.44
    third
    0.44
    molecular
    0.44
    Activations Density 0.002%

    No Known Activations