© 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. 153598
    Prev
    Next
    INDEX
    Explanations

    famous integrated lovers

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

    cost control retail trends evaluation

    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
     번
    0.56
     가져
    0.49
    gateTime
    0.49
    번호
    0.48
     보유
    0.48
     은행
    0.48
     노트
    0.47
     가지
    0.47
     ร้อย
    0.46
     시장
    0.46
    POSITIVE LOGITS
    س
    0.55
    ين
    0.54
    ના
    0.54
    يل
    0.51
    You
    0.51
    يد
    0.50
    の
    0.50
    的
    0.49
    f
    0.49
    ва
    0.49
    Activations Density 0.000%

    No Known Activations