© 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. 17676
    Prev
    Next
    INDEX
    Explanations

    description of features

    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
    <unused1894>
    0.48
     indígen
    0.47
    轮回
    0.46
    сто
    0.45
     implementação
    0.45
    نے
    0.44
     жизни
    0.44
     накло
    0.44
     национа
    0.44
     Kamane
    0.43
    POSITIVE LOGITS
    ↵
    0.48
    د
    0.45
     prickly
    0.45
    工事
    0.42
     Cold
    0.42
     poter
    0.41
     auto
    0.40
     Ser
    0.40
     stress
    0.40
    ユー
    0.40
    Activations Density 0.003%

    No Known Activations