© 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. 199954
    Prev
    Next
    INDEX
    Explanations

    delivery, dates, business

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

    documentation and schema

    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
     Vero
    0.50
     verdana
    0.50
     specifiche
    0.47
    OGR
    0.47
     дори
    0.46
    переди
    0.45
    Qw
    0.45
    <0x0B>
    0.44
     quies
    0.44
     underlie
    0.44
    POSITIVE LOGITS
    ovan
    0.50
    ัก
    0.47
     construction
    0.47
     friendship
    0.46
     Construction
    0.45
     Law
    0.44
    ecu
    0.44
     political
    0.43
     before
    0.43
    iné
    0.43
    Activations Density 0.000%

    No Known Activations