© 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. 58035
    Prev
    Next
    INDEX
    Explanations

    layers and learning

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

    predicting `num_classes`

    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
    mxCell
    0.47
    েন্দু
    0.46
     یورپی
    0.45
    欧
    0.42
    Undefined
    0.42
     সম্পাদিত
    0.41
     ആഘോഷ
    0.41
    鸢
    0.40
     Planning
    0.40
    سبة
    0.40
    POSITIVE LOGITS
     sleepers
    0.46
     flicker
    0.45
     randomNumber
    0.45
     crumble
    0.44
     monies
    0.44
     المبلغ
    0.43
     tunnel
    0.43
     redemption
    0.43
     redir
    0.42
     Kentucky
    0.42
    Activations Density 0.002%

    No Known Activations