© 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. 131985
    Prev
    Next
    INDEX
    Explanations

    driving trash

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

    shrink or stand your ground

    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
    árd
    0.48
    实现
    0.43
    sinya
    0.41
    争
    0.40
    ssss
    0.40
    課
    0.39
    لى
    0.39
    ineries
    0.39
    🦖
    0.39
    ސ
    0.39
    POSITIVE LOGITS
     バイ
    0.59
     керами
    0.58
     바이
    0.53
    HAD
    0.53
     аўта
    0.52
    at
    0.52
    ER
    0.51
    ognito
    0.51
     ทำให้
    0.50
    YNAMICS
    0.49
    Activations Density 0.001%

    No Known Activations