Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 38286
    Prev
    Next
    INDEX
    Explanations

    both sides

    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_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
    أ
    0.93
    Οι
    0.91
    giant
    0.79
     kuten
    0.78
    webpack
    0.77
    І
    0.77
    В
    0.77
    №
    0.76
    i
    0.75
    А
    0.75
    POSITIVE LOGITS
     admissibility
    1.04
     vistas
    0.95
     signings
    0.94
     factories
    0.92
     suitors
    0.91
     descuentos
    0.89
     manifestaciones
    0.88
     típ
    0.88
     reformas
    0.86
     fieles
    0.86
    Activations Density 0.000%

    No Known Activations