© 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. 31-GEMMASCOPE-2-RES-16K
    4. 9559
    Prev
    Next
    INDEX
    Explanations

    tables and structured data

    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_31_width_16k_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
     acknow
    0.70
     accom
    0.67
     construc
    0.64
     administra
    0.60
    3
    0.58
    4
    0.56
    かもし
    0.56
    2
    0.56
    ь
    0.55
    à
    0.55
    POSITIVE LOGITS
     Immunohist
    0.47
    issaient
    0.46
    データベース
    0.46
     Cnemidophorus
    0.44
    माजिक
    0.44
     Elektrokhimiya
    0.43
     ១
    0.42
     نحاول
    0.42
     trialComponents
    0.41
     例如
    0.41
    Activations Density 0.215%

    No Known Activations