© 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. 234702
    Prev
    Next
    INDEX
    Explanations

    before evaluating or calculating

    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
     Gone
    0.48
    விட்டார்
    0.47
    Expanding
    0.47
     pouvant
    0.46
    蜃
    0.45
    仕様
    0.44
     вже
    0.44
     fiabilité
    0.43
    ᱡ
    0.43
    毌
    0.43
    POSITIVE LOGITS
    createUser
    0.48
    មនុស្ស
    0.48
     people
    0.48
    SRP
    0.47
    atop
    0.46
    alertDialog
    0.45
    BY
    0.45
     (.)
    0.44
    UD
    0.44
    IService
    0.44
    Activations Density 0.001%

    No Known Activations