© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 193791
    Prev
    Next
    INDEX
    Explanations

    official certification and opening

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

    costs and business operations

    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
    x
    0.62
    ###
    0.54
     ###
    0.52
     lives
    0.51
     Game
    0.51
     fs
    0.51
     MMA
    0.50
    fm
    0.50
     Lives
    0.50
     std
    0.50
    POSITIVE LOGITS
    すでに
    0.47
    觴
    0.46
     그러나
    0.45
    orescence
    0.45
     ಆರ್
    0.44
    ኙ
    0.43
     구현
    0.43
     하늘
    0.43
     മാത്രമല്ല
    0.43
     баста
    0.42
    Activations Density 0.001%

    No Known Activations