© 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. 43467
    Prev
    Next
    INDEX
    Explanations

    checks and balances

    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
     olen
    -1.29
     Empfindung
    -1.29
     merkwür
    -1.29
    Donativos
    -1.18
     any
    -1.16
    enburg
    -1.13
     Deinen
    -1.13
    瑧
    -1.13
     many
    -1.12
    Many
    -1.12
    POSITIVE LOGITS
    >
    1.33
    ै
    1.28
    obtained
    1.26
    originally
    1.25
    <em>
    1.24
     основных
    1.23
    chauff
    1.22
    against
    1.21
    quickly
    1.20
    蛱
    1.19
    Activations Density 0.031%

    No Known Activations