© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 83001
    Prev
    Next
    INDEX
    Explanations

    SNMP management object identifiers

    np_acts-logits-general · gemini-2.5-flash-lite

    list, comma, and

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     berth
    0.45
     stable
    0.42
    는
    0.42
     departure
    0.40
    棚
    0.39
     reception
    0.38
    வான்
    0.38
    眠
    0.38
    ージャー
    0.38
    聞
    0.38
    POSITIVE LOGITS
     talleres
    0.52
     مجموعة
    0.51
    ܥ
    0.49
     unités
    0.48
    dades
    0.48
    brit
    0.47
     Sava
    0.46
    ۇل
    0.46
    ඹ
    0.46
     الذين
    0.46
    Activations Density 0.003%

    No Known Activations