© 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. 233851
    Prev
    Next
    INDEX
    Explanations

    selling or publishing

    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
    vocab
    0.49
    verbose
    0.48
    perf
    0.48
    pale
    0.48
    farbe
    0.47
    imgur
    0.47
    ($_
    0.47
    concentration
    0.46
    Cantidad
    0.46
    permutation
    0.46
    POSITIVE LOGITS
     cruciate
    0.54
    ى
    0.53
     disorders
    0.52
     Disorders
    0.50
    τές
    0.48
     a
    0.48
     Vũ
    0.47
    迎え
    0.47
     tòa
    0.46
     articular
    0.46
    Activations Density 0.001%

    No Known Activations