© 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
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 38661
    Prev
    Next
    INDEX
    Explanations

    surrounding

    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
    ים
    2.25
    ের
    1.87
     summon
    1.83
    ра
    1.82
    ات
    1.78
    すすめ
    1.73
    í
    1.73
    样的
    1.71
    ulos
    1.70
     saints
    1.70
    POSITIVE LOGITS
    क
    2.09
    t
    2.02
    lagen
    1.89
    cita
    1.88
    并在
    1.88
    ితి
    1.88
    jų
    1.88
    pa
    1.84
    mdash
    1.83
     введен
    1.81
    Activations Density 0.006%

    No Known Activations