© 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. 10984
    Prev
    Next
    INDEX
    Explanations

    child sexual abuse

    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
    on
    0.73
    મ
    0.70
     मम्मी
    0.58
    തിനുള്ള
    0.57
    ה
    0.56
     lanjut
    0.54
    та
    0.54
     χρόνια
    0.54
    を読む
    0.54
     conductas
    0.53
    POSITIVE LOGITS
    swear
    0.78
    r
    0.70
    }.
    0.58
    {
    0.57
    ود
    0.56
    ographic
    0.55
    iyim
    0.55
    ().
    0.54
    راءة
    0.54
    jší
    0.53
    Activations Density 0.165%

    No Known Activations