© 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. 68535
    Prev
    Next
    INDEX
    Explanations

    versions, application, until, internet, children, Commands, Board

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

    learning algorithm and exceptions

    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
    Endereco
    0.53
    ማ
    0.51
    Altura
    0.50
    {|\
    0.49
    ни
    0.47
     При
    0.47
    чис
    0.47
     ανα
    0.47
    昕
    0.47
    Grid
    0.47
    POSITIVE LOGITS
    sounds
    0.52
    log
    0.51
     valuable
    0.51
    thirty
    0.49
    between
    0.49
    matched
    0.49
     hundreds
    0.48
    becomes
    0.48
     dozens
    0.48
    say
    0.47
    Activations Density 0.002%

    No Known Activations