© 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. 144820
    Prev
    Next
    INDEX
    Explanations

    economic terms, software requests, tract activities

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

    dates, companies, CPU, distributed

    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
    laat
    0.51
     І
    0.41
     السي
    0.41
     Ð
    0.41
     رؤ
    0.40
     الحكم
    0.39
     خوا
    0.39
     IELTS
    0.39
    Image
    0.38
     দেখবেন
    0.38
    POSITIVE LOGITS
    ીર
    0.52
     pousse
    0.50
    ченный
    0.50
     rails
    0.48
     piety
    0.48
     poziomie
    0.47
    かつ
    0.47
    麸
    0.46
    inata
    0.46
    பால்
    0.46
    Activations Density 0.000%

    No Known Activations