© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 85674
    Prev
    Next
    INDEX
    Explanations

    negative self-perception

    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_10/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
     a
    -2.14
     our
    -1.65
     sufre
    -1.63
     recibirá
    -1.60
    sandalias
    -1.59
     beträ
    -1.55
    ごちそう
    -1.54
     consigue
    -1.53
                    
    -1.52
     AFTER
    -1.52
    POSITIVE LOGITS
    5
    1.59
    4
    1.57
     hende
    1.54
    6
    1.53
     lyk
    1.50
    tigte
    1.48
     for
    1.46
     fers
    1.44
     tryck
    1.43
     corsa
    1.41
    Activations Density 0.004%

    No Known Activations