© 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. 150770
    Prev
    Next
    INDEX
    Explanations

    exposing APIs and endpoints

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

    exposing APIs and services

    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
    ዣ
    0.57
    ies
    0.56
    ofile
    0.53
    ě
    0.51
    oben
    0.51
    ruč
    0.50
    बंधित
    0.50
    ling
    0.50
    бели
    0.49
    endige
    0.49
    POSITIVE LOGITS
     resistors
    0.63
     capacitor
    0.57
     pasa
    0.55
     resistor
    0.54
     coco
    0.52
     NACA
    0.52
     germanium
    0.52
     cocon
    0.51
    :
    0.51
     dipole
    0.50
    Activations Density 0.000%

    No Known Activations