© 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-65K
    4. 48253
    Prev
    Next
    INDEX
    Explanations

    reports, items, code, shirts, games, policies, vehicles, instructions, containers, community

    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_65k_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
    ਝ
    0.43
    
    0.41
    difficult
    0.40
    кер
    0.38
    slider
    0.38
     виконав
    0.38
    ਪ
    0.38
    对我
    0.38
    brella
    0.38
     komplik
    0.37
    POSITIVE LOGITS
     are
    0.53
     đều
    0.50
     lineup
    0.50
     our
    0.47
    都是
    0.47
     наших
    0.47
     janë
    0.47
     Nuestros
    0.46
     flagship
    0.46
    均为
    0.46
    Activations Density 0.104%

    No Known Activations