© 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. 142801
    Prev
    Next
    INDEX
    Explanations

    saving options

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

    counting numbers in lists

    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
    复杂的
    0.57
    肿瘤
    0.53
    律师
    0.52
    胀
    0.52
    Ac
    0.49
    AB
    0.49
    复杂
    0.48
    AG
    0.48
    庆祝
    0.47
    醸
    0.47
    POSITIVE LOGITS
     zoek
    0.49
     bestimm
    0.49
     Джу
    0.48
     لیے
    0.47
     Rakh
    0.47
    (),"
    0.47
     حص
    0.46
     Nok
    0.46
     К
    0.46
     Neben
    0.46
    Activations Density 0.001%

    No Known Activations