© 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. 60702
    Prev
    Next
    INDEX
    Explanations

    names starting with Dave

    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
    s
    -2.97
    </h4>
    -2.48
     bekannten
    -2.44
    縯
    -2.41
    n
    -2.41
     Rückseite
    -2.41
    ஂ
    -2.39
     einzigartigen
    -2.30
     We
    -2.22
    蛧
    -2.22
    POSITIVE LOGITS
     Chinois
    2.75
     uſed
    2.63
     Founded
    2.56
     anfitrión
    2.53
     pittores
    2.52
     If
    2.50
    ТЫ
    2.42
     littéraire
    2.41
     consegui
    2.41
     AFTER
    2.36
    Activations Density 0.007%

    No Known Activations