© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 70738
    Prev
    Next
    INDEX
    Explanations

    World Wide Web

    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
     the
    -2.83
     how
    -2.38
     instead
    -1.55
     että
    -1.49
     your
    -1.49
     who
    -1.47
     want
    -1.46
    Proyectos
    -1.45
     these
    -1.38
     superfí
    -1.38
    POSITIVE LOGITS
     noin
    1.38
     on
    1.34
    ISTRATION
    1.32
     Parlement
    1.31
    ourcen
    1.31
    мия
    1.30
     +
    1.30
    <td>
    1.28
    YNAMIC
    1.28
     повседнев
    1.27
    Activations Density 0.113%

    No Known Activations