© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 98501
    Prev
    Next
    INDEX
    Explanations

    percentage calculation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    вое
    0.34
    ﻅ
    0.34
    ンの
    0.33
    cht
    0.31
    ิ
    0.31
    ת
    0.31
    ﺼ
    0.31
    帕
    0.31
    มน
    0.30
     lineage
    0.30
    POSITIVE LOGITS
     indicó
    0.39
     said
    0.38
     dijo
    0.37
     noted
    0.36
     November
    0.34
    ”
    0.34
     says
    0.33
     thịt
    0.33
    ’
    0.33
     Wednesday
    0.33
    Activations Density 0.007%

    No Known Activations