© 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. 49136
    Prev
    Next
    INDEX
    Explanations

    thanks to you

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

    creating games and systems

    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
    est
    0.50
    }^{
    0.47
    io
    0.46
    len
    0.46
    product
    0.45
    eq
    0.44
    is
    0.44
     eventual
    0.43
     histories
    0.43
     product
    0.42
    POSITIVE LOGITS
    微软
    0.49
    贼
    0.46
    电源
    0.46
     स्वत
    0.45
    Biscuit
    0.44
     创建
    0.44
    战士
    0.43
    层
    0.43
     stwor
    0.42
     ennemis
    0.42
    Activations Density 0.000%

    No Known Activations