© 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. 13461
    Prev
    Next
    INDEX
    Explanations

    source code

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

    source code

    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
     biomarker
    0.37
     ™
    0.36
     Remover
    0.35
     biomarkers
    0.34
     movers
    0.34
     AMOLED
    0.34
     coined
    0.34
     personalizar
    0.33
     detections
    0.33
     মাঝামা
    0.33
    POSITIVE LOGITS
    䢍
    0.35
    ਰਾ
    0.34
     રાખ
    0.34
     unchanged
    0.34
    этому
    0.33
     זאת
    0.33
    ่านั้น
    0.33
     যতদিন
    0.33
    诒
    0.33
    Camping
    0.32
    Activations Density 0.000%

    No Known Activations