© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 50436
    Prev
    Next
    INDEX
    Explanations

    reports is Uber

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

    resources and constraints

    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
     Osim
    0.45
    भूषण
    0.42
     unbearable
    0.40
     Além
    0.40
     intensifying
    0.40
    у
    0.40
    밖
    0.40
    ás
    0.39
    楽天市場
    0.39
     alleviating
    0.39
    POSITIVE LOGITS
    iou
    0.41
     আগামী
    0.38
    誡
    0.37
     chick
    0.37
    setCellValue
    0.37
    "},
    0.37
    _{-
    0.36
    يته
    0.36
    "};
    0.36
    NOWLED
    0.36
    Activations Density 0.000%

    No Known Activations