© 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. 40-GEMMASCOPE-2-RES-65K
    7. 849
    Prev
    Next
    INDEX
    Explanations

    sexual assault

    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_65k_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
    掩
    0.38
     प्रेग्नेंसी
    0.38
    spra
    0.38
    SPs
    0.38
    нете
    0.36
    obos
    0.36
    zuführen
    0.36
     grosseur
    0.36
     Berc
    0.36
    ĵ
    0.35
    POSITIVE LOGITS
     violence
    0.50
    Violence
    0.49
     violência
    0.48
     Violence
    0.47
     assault
    0.44
     हिंसा
    0.43
     violencia
    0.39
    violence
    0.39
     shout
    0.38
     Gewalt
    0.37
    Activations Density 0.083%

    No Known Activations