© 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. 113262
    Prev
    Next
    INDEX
    Explanations

    related to installation or numbers

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

    depend on

    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
     naw
    0.48
    lobin
    0.48
     Recommendation
    0.46
     kitap
    0.46
     conseille
    0.46
     추천
    0.46
     adolesc
    0.46
     책
    0.46
     ade
    0.46
     told
    0.45
    POSITIVE LOGITS
    ByUser
    0.50
    agements
    0.46
     Saito
    0.45
    充满
    0.45
    UpDown
    0.44
    充滿
    0.44
     uniquely
    0.43
     SVM
    0.43
    全新的
    0.43
    ებისა
    0.43
    Activations Density 0.001%

    No Known Activations