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. 8206
    Prev
    Next
    INDEX
    Explanations

    news publication names

    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
    ir
    1.14
    م
    1.05
    ا
    1.02
    に
    0.95
    一系列
    0.94
    ü
    0.93
    é
    0.93
    다
    0.92
    र्
    0.91
    и
    0.91
    POSITIVE LOGITS
     payee
    0.82
    “,
    0.77
     potrebno
    0.73
     headcount
    0.73
     fratt
    0.72
     verifica
    0.71
    땃
    0.70
     detr
    0.69
     floats
    0.69
    дт
    0.68
    Activations Density 0.001%

    No Known Activations