© 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. 49793
    Prev
    Next
    INDEX
    Explanations

    World Showcase

    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
     niew
    0.50
     председа
    0.50
     Ries
    0.47
     повышение
    0.46
    otive
    0.45
     당시
    0.44
    ěr
    0.44
    >;
    0.42
     ря
    0.42
     носи
    0.42
    POSITIVE LOGITS
    c
    0.57
    a
    0.57
    א
    0.52
    continues
    0.48
    context
    0.48
    ه
    0.47
    ون
    0.47
    ಾರ್ಟ
    0.47
    INSERT
    0.46
    鋆
    0.46
    Activations Density 0.001%

    No Known Activations