© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 111775
    Prev
    Next
    INDEX
    Explanations

    key concepts and terms

    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
     නව
    0.46
    깼
    0.44
    ോളം
    0.42
     newdata
    0.39
     ስለዚህ
    0.39
    nPlease
    0.38
     mesti
    0.38
     irgendwo
    0.38
    తిరే
    0.37
     desesper
    0.37
    POSITIVE LOGITS
    /\
    0.36
    爍
    0.36
    /
    0.35
    平
    0.35
    ongo
    0.35
    業務
    0.35
    igations
    0.35
     সংক্রান্ত
    0.35
    POP
    0.34
     pénétr
    0.33
    Activations Density 0.000%

    No Known Activations