© 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. 16-GEMMASCOPE-2-RES-262K
    7. 17891
    Prev
    Next
    INDEX
    Explanations

    sink

    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_16_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
    ット
    0.69
     pushing
    0.61
     démarrage
    0.59
     predisposition
    0.59
     tissu
    0.57
    敚
    0.55
    ình
    0.55
     moderno
    0.55
    のない
    0.53
     запас
    0.53
    POSITIVE LOGITS
    s
    0.70
    س
    0.70
    ف
    0.70
     Relation
    0.68
    و
    0.67
     Data
    0.64
     Sites
    0.64
    ะ
    0.63
    स
    0.62
    ”
    0.61
    Activations Density 0.001%

    No Known Activations