© 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. 180642
    Prev
    Next
    INDEX
    Explanations

    the code `and` `and` `language`

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

    programming and scraping

    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
     organizaciones
    0.55
    <unused55>
    0.55
     fiducia
    0.54
     consente
    0.54
     sizlerle
    0.53
     pozwala
    0.53
    ার্থীরা
    0.53
    <unused23>
    0.52
     fechas
    0.52
    <unused29>
    0.52
    POSITIVE LOGITS
     an
    0.54
    ;
    0.53
    Life
    0.50
    1
    0.48
                                   
    0.47
    Bra
    0.46
    Liverpool
    0.46
    8
    0.46
    7
    0.46
    hö
    0.45
    Activations Density 0.000%

    No Known Activations