© 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. 138535
    Prev
    Next
    INDEX
    Explanations

    patient eyes

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

    reverse proxy, programs, tables, bidding

    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
     αυτή
    0.45
     உள்ளார்
    0.45
     წარმო
    0.44
    5
    0.44
     prati
    0.43
    狷
    0.43
     Proctor
    0.42
     Observer
    0.42
     ফিল্ম
    0.42
     obscur
    0.42
    POSITIVE LOGITS
    att
    0.45
    shore
    0.45
    mux
    0.44
    ot
    0.44
    gar
    0.43
    р
    0.43
    az
    0.43
    sea
    0.43
    pipe
    0.43
    JE
    0.42
    Activations Density 0.001%

    No Known Activations