© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 81016
    Prev
    Next
    INDEX
    Explanations

    sports matches

    np_acts-logits-general · gemini-2.5-flash-lite

    quantized events and superintelligence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Statement
    0.45
    iform
    0.44
    𝙜
    0.44
    StartPosition
    0.44
     ყ
    0.43
    ถาน
    0.43
    Backward
    0.41
    岂
    0.41
    ادم
    0.41
    ادت
    0.40
    POSITIVE LOGITS
     Sega
    0.49
     পারে
    0.49
     दुसरे
    0.49
     AFL
    0.49
    レザー
    0.48
     پیسے
    0.48
     অস্ট্র
    0.47
     différentes
    0.46
     বেশিরভাগ
    0.46
     který
    0.46
    Activations Density 0.001%

    No Known Activations