© 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. 163460
    Prev
    Next
    INDEX
    Explanations

    Chester Bennington

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

    Fourier's mathematical context

    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
    复杂度
    0.49
    andfeel
    0.45
    怿
    0.45
     idiots
    0.44
     andDevice
    0.44
    忧
    0.44
    "};
    0.43
    แต่
    0.43
     اكثر
    0.43
    最优
    0.43
    POSITIVE LOGITS
    packaged
    0.46
    S
    0.45
    B
    0.44
    protos
    0.43
    M
    0.43
     These
    0.42
     físico
    0.42
     tyto
    0.42
    K
    0.42
    fragment
    0.41
    Activations Density 0.001%

    No Known Activations