© 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. 89217
    Prev
    Next
    INDEX
    Explanations

    know what there is

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

    AML, warnings, security concerns

    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
     imagen
    0.49
     ơi
    0.46
    ("${
    0.45
     académico
    0.45
     exige
    0.44
     pasó
    0.44
     sạch
    0.44
     další
    0.43
    到一个
    0.43
     excepto
    0.43
    POSITIVE LOGITS
     Defining
    0.52
     deleterious
    0.46
    廟
    0.46
     sipping
    0.46
    養
    0.44
     Substituting
    0.44
    鏗
    0.44
    ordinating
    0.43
    vering
    0.42
     phenolic
    0.42
    Activations Density 0.000%

    No Known Activations