© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 13956
    Prev
    Next
    INDEX
    Explanations

    rape, abuse, violencehotlines

    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
     Ihrem
    0.39
     resten
    0.38
    <unused6>
    0.38
    wane
    0.38
    㐌
    0.37
     quorum
    0.37
    惆
    0.37
     फट
    0.37
     اس
    0.36
    𒂵
    0.36
    POSITIVE LOGITS
    ea
    0.40
    =-
    0.39
     =
    0.38
    iar
    0.36
     wasn
    0.35
    atr
    0.35
    >\
    0.35
    eny
    0.35
    OU
    0.35
    ;
    0.34
    Activations Density 0.052%

    No Known Activations