© 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. 53600
    Prev
    Next
    INDEX
    Explanations

    personal or financial descriptions

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

    economic topics

    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
    she
    0.50
    ξης
    0.48
    Grouping
    0.47
     celles
    0.47
    리
    0.47
    row
    0.46
    ಟ
    0.46
    at
    0.45
    ان
    0.45
    oci
    0.45
    POSITIVE LOGITS
     hatchback
    0.55
     deflation
    0.54
     banks
    0.52
     tatsächlich
    0.52
     northeast
    0.50
     fracking
    0.49
     preseason
    0.48
     realty
    0.48
     wirelessly
    0.48
     определён
    0.47
    Activations Density 0.000%

    No Known Activations