© 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. 148676
    Prev
    Next
    INDEX
    Explanations

    older people

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

    OpenAPI specifications, hair regrowth, rocket motor

    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
    股
    0.53
    裕
    0.45
    计
    0.44
     Chartered
    0.42
    注册
    0.42
     provisioning
    0.41
     goggles
    0.41
    意义
    0.40
    র্যের
    0.40
     ferro
    0.39
    POSITIVE LOGITS
     anisotropy
    0.49
    オススメ
    0.48
     выращи
    0.48
     \{
    0.45
    MAGNET
    0.45
     তোমাদের
    0.44
    imą
    0.44
    StartPosition
    0.44
    বয়
    0.44
     Fiziki
    0.43
    Activations Density 0.001%

    No Known Activations