© 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. 49428
    Prev
    Next
    INDEX
    Explanations

    young minds, installation, Windows, ultimate guide, portugal

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

    datasets import

    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
     d
    0.54
     is
    0.51
     coveted
    0.47
     scanned
    0.45
     took
    0.44
     competed
    0.44
    Harrison
    0.42
     glanced
    0.42
     aspires
    0.42
     revoked
    0.42
    POSITIVE LOGITS
    مو
    0.55
    品番
    0.51
    ناد
    0.51
    メッセージ
    0.50
    ن
    0.48
    உலக
    0.48
    峻
    0.48
    蛋白質
    0.48
    現金
    0.47
    شوند
    0.47
    Activations Density 0.000%

    No Known Activations