© 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. 62016
    Prev
    Next
    INDEX
    Explanations

    questions followed by felicity

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

    always run, refers to, try to

    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
    літи
    0.57
    міні
    0.53
    stakes
    0.49
     смартфон
    0.49
    涜
    0.49
     валю
    0.47
    ктор
    0.47
     അദ്ദേ
    0.47
     місто
    0.47
    ⺌
    0.47
    POSITIVE LOGITS
     di
    0.48
     de
    0.48
     crim
    0.47
     Agricultura
    0.47
     évident
    0.47
     obt
    0.46
     Raghav
    0.46
     જેથી
    0.45
     layout
    0.45
     kuj
    0.45
    Activations Density 0.000%

    No Known Activations