© 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. 25299
    Prev
    Next
    INDEX
    Explanations

    White, Town, Alessandro, Billy

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

    examples of code

    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
     Reiter
    0.45
     diskut
    0.44
    /
    0.43
     ਦੇ
    0.43
     े
    0.43
     koska
    0.41
     discuter
    0.41
     introductory
    0.41
     навчання
    0.41
     multit
    0.40
    POSITIVE LOGITS
    BIR
    0.54
    Town
    0.52
    монт
    0.51
    White
    0.49
    Billy
    0.47
    atown
    0.46
    Alessandro
    0.46
    凯
    0.46
    WHITE
    0.46
    白的
    0.45
    Activations Density 0.000%

    No Known Activations