© 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. 38675
    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
    ж
    0.79
    أ
    0.77
    براین
    0.73
     gelijk
    0.73
     schon
    0.73
    ية
    0.71
     nakon
    0.71
     somos
    0.70
     biedt
    0.69
     diffère
    0.69
    POSITIVE LOGITS
     hoisted
    0.95
     acidified
    0.94
    ט
    0.94
     patric
    0.93
    cart
    0.87
     Ủy
    0.86
    thoughts
    0.84
    lived
    0.84
     crested
    0.83
    cargar
    0.82
    Activations Density 0.000%

    No Known Activations