© 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. 31-GEMMASCOPE-2-RES-65K
    7. 3569
    Prev
    Next
    INDEX
    Explanations

    html structures and descriptions

    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
    戕
    0.48
    Room
    0.47
    Despatx
    0.46
    elho
    0.45
    шка
    0.45
    RELATIVA
    0.44
    stamp
    0.43
    黢
    0.43
     coordin
    0.43
    ból
    0.42
    POSITIVE LOGITS
     سرعت
    0.48
     منت
    0.47
     প্রচুর
    0.46
     ت
    0.45
     நிறைய
    0.45
    ieren
    0.45
     скорости
    0.45
    一些
    0.44
     many
    0.44
     وت
    0.44
    Activations Density 0.008%

    No Known Activations