© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 11127
    Prev
    Next
    INDEX
    Explanations

    pearlescent

    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
    郆
    0.50
    鸣
    0.50
    㸳
    0.49
    の手
    0.48
    httpRequest
    0.48
    FreeBuf
    0.48
    MemoryWarning
    0.47
    杽
    0.47
     灯
    0.46
    έργ
    0.46
    POSITIVE LOGITS
     database
    0.48
    ↵
    0.46
     silver
    0.45
    '
    0.45
     tracking
    0.44
     carbon
    0.44
    system
    0.44
     axle
    0.44
    ?
    0.44
     platform
    0.43
    Activations Density 0.000%

    No Known Activations