© 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-3-12B-IT
    5. 24-GEMMASCOPE-2-RES-262K
    7. 1760
    Prev
    Next
    INDEX
    Explanations

    explicit sexual content and descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_24_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
     horsepower
    0.75
    ↵
    0.75
     electrom
    0.75
     throughput
    0.69
    !
    0.67
    0.65
     a
    0.65
     goodies
    0.65
    '
    0.63
     batch
    0.62
    POSITIVE LOGITS
     Feminist
    1.10
     Sensitive
    1.02
     feminist
    1.02
     Sexuality
    1.01
     Violence
    1.00
     SEXUAL
    0.98
    Violence
    0.97
    Sensitive
    0.97
    Sexual
    0.96
     Kontext
    0.94
    Activations Density 0.009%

    No Known Activations