© 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. 1540
    Prev
    Next
    INDEX
    Explanations

    $_POST, $_GET, $_FILES

    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
    ৪
    2.30
    いた
    2.13
    ни
    2.03
    ﺮ
    1.99
    ﺪ
    1.94
    ﻄ
    1.91
    মী
    1.88
    ாக
    1.86
    ிறது
    1.84
    age
    1.80
    POSITIVE LOGITS
    i
    2.70
    ه
    2.48
    ে
    2.30
    ש
    2.11
    ி
    1.89
    то
    1.73
    هي
    1.66
    していますが
    1.65
    ర్
    1.64
    ğ
    1.62
    Activations Density 0.004%

    No Known Activations