© 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. 169735
    Prev
    Next
    INDEX
    Explanations

    table top

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

    the Data Analysis Toolpak

    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
     패턴
    0.61
    雰
    0.60
    됩니다
    0.58
    gateTime
    0.57
    㓦
    0.54
     парла
    0.52
     அணிய
    0.52
     테이블
    0.52
     확률
    0.52
     მხოლოდ
    0.52
    POSITIVE LOGITS
    la
    0.64
    i
    0.58
    '
    0.55
    lo
    0.52
    zk
    0.52
    ai
    0.50
    ink
    0.50
    ah
    0.47
    ze
    0.47
    tai
    0.47
    Activations Density 0.000%

    No Known Activations