© 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. 16-GEMMASCOPE-2-RES-262K
    7. 46533
    Prev
    Next
    INDEX
    Explanations

    pornography addiction

    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_16_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
    AN
    0.93
    ஜ்மஹால்
    0.91
    EN
    0.80
    OF
    0.79
    でした
    0.78
    ド
    0.76
    ０
    0.76
    MeToo
    0.75
    です
    0.73
    ஜ்மஹ
    0.73
    POSITIVE LOGITS
    ↵
    1.25
    ש
    1.15
     E
    1.07
    -
    0.89
     مكان
    0.84
    (
    0.83
    ير
    0.81
    la
    0.80
    ط
    0.79
    تك
    0.77
    Activations Density 0.006%

    No Known Activations