© 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. 6710
    Prev
    Next
    INDEX
    Explanations

    specific item names

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

    APIs, database, or network carriers

    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
     newApproved
    0.29
     hoera
    0.28
     nasceu
    0.28
    <unused2148>
    0.28
     prenez
    0.27
     paysans
    0.27
     myster
    0.27
     télévision
    0.27
     résult
    0.27
     wollen
    0.27
    POSITIVE LOGITS
    1
    0.37
    3
    0.33
    6
    0.32
    5
    0.31
    7
    0.29
    4
    0.29
    categories
    0.29
    sub
    0.28
    un
    0.27
    ol
    0.27
    Activations Density 0.548%

    No Known Activations