© 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. 42214
    Prev
    Next
    INDEX
    Explanations

    technical terms describing inventions

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

    Data Studio, hacks, why

    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
    为
    0.59
     są
    0.57
     można
    0.55
    érica
    0.54
     będą
    0.52
     która
    0.52
     ország
    0.52
     rekomend
    0.50
     irão
    0.49
     deverá
    0.48
    POSITIVE LOGITS
    Phil
    0.47
     Phil
    0.46
     চীনা
    0.45
    yama
    0.45
     H
    0.45
    พร
    0.45
    醤
    0.45
     حتی
    0.44
     絵
    0.44
    ೇಶ್
    0.44
    Activations Density 0.000%

    No Known Activations