© 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
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 38692
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
    ⴻ
    1.03
     comandos
    1.01
     spinors
    0.95
     marav
    0.89
    ၆
    0.89
     где
    0.88
     polít
    0.87
     considerado
    0.87
     FERC
    0.87
     FHWA
    0.86
    POSITIVE LOGITS
    ine
    1.27
    h
    0.93
    Dictionary
    0.91
    hold
    0.89
    LL
    0.88
    icación
    0.86
    ent
    0.84
    ate
    0.84
    dem
    0.84
    age
    0.83
    Activations Density 0.000%

    No Known Activations