© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 9456
    Prev
    Next
    INDEX
    Explanations

    and explanations

    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_31_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
     womb
    0.39
     zada
    0.38
     Dewan
    0.37
     planetary
    0.37
     domains
    0.36
     Зем
    0.35
     ಪುಸ್ತಕ
    0.35
    汹
    0.35
     최대한
    0.35
     circulatory
    0.34
    POSITIVE LOGITS
    删除
    0.60
     delete
    0.60
    delete
    0.59
    Delete
    0.58
     删除
    0.57
     Delete
    0.52
     outright
    0.50
     삭제
    0.48
     deleting
    0.47
    刪
    0.47
    Activations Density 0.276%

    No Known Activations