© 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. 190597
    Prev
    Next
    INDEX
    Explanations

    valuations, applicable information

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

    translation and degradation

    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
    ဏ်
    0.46
     Fernandez
    0.45
     শিক্ষা
    0.44
    $("#
    0.43
    farwydd
    0.43
    匐
    0.43
    COLUMN
    0.43
    斯的
    0.43
    ట్టు
    0.42
    Hlav
    0.42
    POSITIVE LOGITS
     величина
    0.54
     вали
    0.52
    값
    0.52
     велико
    0.49
     valuations
    0.48
     valida
    0.48
     ער
    0.48
     результа
    0.47
     куп
    0.46
    ٹنگ
    0.45
    Activations Density 0.000%

    No Known Activations