© 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. 40-GEMMASCOPE-2-RES-262K
    7. 213066
    Prev
    Next
    INDEX
    Explanations

    sexual assault or rape

    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_40_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
    ዳል
    0.39
    ⊡
    0.38
    क्ताओं
    0.38
    াসহ
    0.37
     मैथ
    0.37
     MISS
    0.37
    ректор
    0.37
     सीमाओं
    0.36
    刂
    0.36
     चेयर
    0.36
    POSITIVE LOGITS
     Esse
    0.39
     ness
    0.38
     Inoltre
    0.38
    영화
    0.37
     Queste
    0.36
     Strict
    0.36
     Questo
    0.35
     soc
    0.35
     Там
    0.35
     albo
    0.35
    Activations Density 0.000%

    No Known Activations