© 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. 83394
    Prev
    Next
    INDEX
    Explanations

    financial and legal contexts

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

    benchmarking mode

    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
    t
    0.64
     ti
    0.52
    ,
    0.48
    对于
    0.46
     Ti
    0.46
     Kelly
    0.46
     Husk
    0.46
     t
    0.45
     Hull
    0.45
     Development
    0.44
    POSITIVE LOGITS
    outputPath
    0.54
    हद
    0.54
    ៤
    0.52
    genomen
    0.49
     холоди
    0.47
    wege
    0.46
    ма
    0.46
     இருப்பது
    0.46
    OPERATION
    0.46
    ValMap
    0.46
    Activations Density 0.000%

    No Known Activations