© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 15015
    Prev
    Next
    INDEX
    Explanations

    comparison operators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uo
    -1.11
     of
    -1.03
    ar
    -1.02
    ↵
    -1.02
    を
    -0.99
    li
    -0.98
    u
    -0.94
    amo
    -0.93
    fer
    -0.91
    arão
    -0.90
    POSITIVE LOGITS
     її
    1.20
    ({
    1.07
    études
    1.02
     moest
    1.00
    ZIONI
    0.97
    uteurs
    0.97
     olika
    0.96
    tiven
    0.94
     innehå
    0.94
     pensent
    0.94
    Activations Density 0.012%

    No Known Activations