© 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. 212811
    Prev
    Next
    INDEX
    Explanations

    contact us

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

    PWNED, grey Brazilian, directly access

    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
     Ψ
    0.50
     каз
    0.48
     Ак
    0.47
     我們
    0.47
     下载
    0.47
     আরেক
    0.47
     trafficking
    0.47
     도입
    0.47
     регі
    0.46
     חלק
    0.46
    POSITIVE LOGITS
     és
    0.51
     oči
    0.50
    inten
    0.49
    Records
    0.48
    ؤول
    0.47
    用
    0.46
    ली
    0.46
    련
    0.46
    ردن
    0.46
    пози
    0.45
    Activations Density 0.000%

    No Known Activations