© 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. 38077
    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
    a
    1.14
    u
    1.01
    er
    0.98
    e
    0.97
    y
    0.94
    fted
    0.86
    jší
    0.80
    된
    0.79
    kah
    0.77
    i
    0.77
    POSITIVE LOGITS
    Ticks
    0.94
    મી
    0.89
    SystemCall
    0.89
    Firestore
    0.85
    Glare
    0.84
    รถ
    0.84
     ônibus
    0.84
    Todos
    0.84
    PW
    0.83
     กม
    0.83
    Activations Density 0.000%

    No Known Activations