© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 40553
    Prev
    Next
    INDEX
    Explanations

    rate of work or energy transfer

    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
     Timurtaş
    0.49
     різних
    0.48
     урока
    0.45
     конкре
    0.45
    மனித
    0.45
    более
    0.45
     материалов
    0.44
    齬
    0.44
     있었습니다
    0.44
    ishops
    0.43
    POSITIVE LOGITS
     vassal
    0.50
     estado
    0.48
     disgraced
    0.46
    以及
    0.46
     cia
    0.45
     vaj
    0.45
     inherits
    0.45
     ka
    0.44
     as
    0.44
     Kazakhstan
    0.44
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.