© 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
    5. 31-GEMMASCOPE-2-RES-16K
    7. 9742
    Prev
    Next
    INDEX
    Explanations

    villains

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    尷
    0.72
    尴尬
    0.71
    窘
    0.69
     احتجاج
    0.67
    吵
    0.64
    救援
    0.63
    感动
    0.63
     awkward
    0.62
     awkwardly
    0.62
     courageous
    0.61
    POSITIVE LOGITS
     satan
    1.77
     sadistic
    1.73
     Satan
    1.63
     demonic
    1.63
     evil
    1.61
    😈
    1.59
     Evil
    1.51
    👿
    1.51
     sinister
    1.48
     murderous
    1.48
    Activations Density 0.505%

    No Known Activations