© 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-262K
    7. 6851
    Prev
    Next
    INDEX
    Explanations

    deeply harmful or dangerous

    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_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
    能够
    0.41
    能
    0.40
    ையுடன்
    0.39
     అందించ
    0.37
    但也
    0.37
    สามารถ
    0.36
    有时候
    0.36
    但
    0.36
    包含
    0.36
     included
    0.35
    POSITIVE LOGITS
     horrific
    0.74
     dreadful
    0.73
     disgraceful
    0.72
     inept
    0.71
     appalling
    0.70
     hopelessly
    0.70
     unacceptable
    0.69
     horrendous
    0.69
     dismal
    0.69
     disgusting
    0.68
    Activations Density 0.558%

    No Known Activations