© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 12851
    Prev
    Next
    INDEX
    Explanations

    SQL, CSV, and generation concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
    ни
    0.52
    ཋ
    0.48
    ст
    0.47
    ]。
    0.47
    жном
    0.46
    се
    0.46
    я
    0.46
    ਂ
    0.46
    日语
    0.46
    轳
    0.45
    POSITIVE LOGITS
    ur
    0.55
    oz
    0.52
    h
    0.51
    ana
    0.50
    er
    0.48
    vey
    0.47
    hale
    0.47
    utherford
    0.46
    hare
    0.46
    lger
    0.46
    Activations Density 0.001%

    No Known Activations