© 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. 55723
    Prev
    Next
    INDEX
    Explanations

    guide wire

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

    coding faster

    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
    ล่าสุด
    0.48
    MaxSize
    0.48
    MaxWidth
    0.47
    recen
    0.47
    recent
    0.46
    Coef
    0.44
    .*
    0.44
    .*/
    0.44
    igable
    0.44
    Proveedor
    0.43
    POSITIVE LOGITS
     generasi
    0.48
     daun
    0.46
     wept
    0.46
     pekerjaan
    0.46
    وند
    0.46
     práci
    0.45
     thalam
    0.44
     Kampung
    0.44
     akan
    0.43
     yazd
    0.43
    Activations Density 0.000%

    No Known Activations