© 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. 19751
    Prev
    Next
    INDEX
    Explanations

    what is a / an

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

    abstract concepts and specific nouns

    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
    +\
    0.52
    жа
    0.49
    зия
    0.48
    UB
    0.46
    喘
    0.44
    ုတ်
    0.44
    ИА
    0.43
    げ
    0.43
    替
    0.43
     ซึ่ง
    0.43
    POSITIVE LOGITS
     Encryption
    0.52
     Auction
    0.51
     idempotent
    0.51
     iteratively
    0.50
     organs
    0.49
     Indirect
    0.49
     custom
    0.48
     solenoid
    0.48
     sputter
    0.48
     SURVEY
    0.48
    Activations Density 0.000%

    No Known Activations