© 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-3-12B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 2618
    Prev
    Next
    INDEX
    Explanations

    negative judgment of intelligence

    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_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
     unintended
    0.72
     DataFrame
    0.68
    ⏸
    0.61
    🔍
    0.60
    风险
    0.60
     might
    0.59
     covert
    0.59
     confidentiality
    0.58
     ہتھی
    0.58
    棂
    0.58
    POSITIVE LOGITS
     stupid
    2.36
     stupidity
    2.13
     disgusting
    2.08
     idiots
    1.99
     Stupid
    1.97
     ridiculous
    1.95
     idiot
    1.93
     foolish
    1.79
     hideous
    1.75
     obnoxious
    1.75
    Activations Density 0.873%

    No Known Activations