© 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. 139155
    Prev
    Next
    INDEX
    Explanations

    names, facts, and places

    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
    Tables
    0.48
    ហ៊
    0.47
    Machine
    0.46
    ل
    0.45
    網絡
    0.44
     digestible
    0.43
    レット
    0.42
     politics
    0.42
     underneath
    0.42
    ៈ
    0.42
    POSITIVE LOGITS
    iado
    0.52
    enie
    0.44
    zb
    0.42
    tipo
    0.42
     پرورش
    0.42
    ije
    0.42
    angkan
    0.42
    iak
    0.42
    leve
    0.41
    ej
    0.41
    Activations Density 0.002%

    No Known Activations