© 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. 53261
    Prev
    Next
    INDEX
    Explanations

    reporting or tracking information

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

    crucial technical or magical tasks

    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
    /
    0.51
    ্কে
    0.50
    選擇
    0.49
    或
    0.49
     offers
    0.48
    left
    0.47
     presence
    0.46
    <code>
    0.46
    或者
    0.46
     eller
    0.46
    POSITIVE LOGITS
     কাগজপত্র
    0.51
     бумаги
    0.49
     diarias
    0.49
    তরাং
    0.49
     trasmissione
    0.49
     ferrugineux
    0.46
    耔
    0.45
     işlemler
    0.44
     interstitiis
    0.44
     impresora
    0.43
    Activations Density 0.000%

    No Known Activations