© 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. 168041
    Prev
    Next
    INDEX
    Explanations

    terms indicating frequency or regularity

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

    Air time effectiveness

    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
    ורים
    0.56
    値を
    0.53
     Valores
    0.52
    werten
    0.52
    揩
    0.52
    欝
    0.51
     Бе
    0.51
    값이
    0.51
    最強
    0.51
     값을
    0.50
    POSITIVE LOGITS
     ordinary
    0.52
     carbure
    0.50
     jelly
    0.47
     brittle
    0.47
     reconstructed
    0.46
     unmarked
    0.46
     sill
    0.45
     periodically
    0.45
     egg
    0.44
     bury
    0.44
    Activations Density 0.000%

    No Known Activations