© 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. 24-GEMMASCOPE-2-RES-262K
    7. 8378
    Prev
    Next
    INDEX
    Explanations

    project structure paths

    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_24_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
     dynamic
    0.75
     from
    0.73
     day
    0.73
    from
    0.73
     severely
    0.73
     dari
    0.71
     saud
    0.70
    e
    0.70
     very
    0.69
    日から
    0.68
    POSITIVE LOGITS
    $/../../
    0.88
    $/../../../../
    0.85
     CMake
    0.82
     Alguns
    0.82
    นั้น
    0.81
    ├──
    0.81
    байд
    0.80
    нің
    0.78
     Algunos
    0.77
    ಮ್ಮ
    0.75
    Activations Density 0.001%

    No Known Activations