© 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. 19222
    Prev
    Next
    INDEX
    Explanations

    financial data, numbers, byte arrays

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

    database schema and coding types

    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
    Methylsulfanyl
    0.66
    辂
    0.60
    嫘
    0.60
    Elater
    0.55
    Prothorax
    0.55
    Pyrimidine
    0.54
    彘
    0.54
    镤
    0.53
     வழிப
    0.52
    Anthrop
    0.52
    POSITIVE LOGITS
    fasterxml
    0.61
    if
    0.55
    omitempty
    0.53
    financial
    0.52
    null
    0.50
     columnist
    0.46
    request
    0.46
    nullable
    0.46
    customer
    0.46
    //
    0.46
    Activations Density 0.000%

    No Known Activations