© 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. 108107
    Prev
    Next
    INDEX
    Explanations

    COBRA applies

    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
     ホ
    0.47
     voisins
    0.46
    gens
    0.45
    ){
    0.45
     oats
    0.44
     buckwheat
    0.44
     изделия
    0.43
    ()){
    0.42
     Gens
    0.41
     sailboats
    0.41
    POSITIVE LOGITS
    am
    0.47
    EN
    0.46
    integration
    0.45
     promotion
    0.44
    지
    0.44
    依存
    0.43
    넌
    0.42
     chairperson
    0.42
    promotion
    0.42
    encoder
    0.41
    Activations Density 0.000%

    No Known Activations