© 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. 41229
    Prev
    Next
    INDEX
    Explanations

    structure for lists

    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
    ms
    0.55
    ad
    0.53
    ly
    0.50
    al
    0.48
    m
    0.48
    als
    0.47
    ming
    0.47
     Beale
    0.46
    ru
    0.46
    {},
    0.45
    POSITIVE LOGITS
    кция
    0.47
     kwenye
    0.46
    блиоте
    0.46
    гина
    0.46
     dérivés
    0.44
     ervan
    0.44
    ้าร
    0.44
    ждую
    0.44
     свойства
    0.44
     nuova
    0.43
    Activations Density 0.000%

    No Known Activations