© 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. 60136
    Prev
    Next
    INDEX
    Explanations

    community service professions

    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
    Specificity
    -1.27
     holotype
    -1.20
    GBR
    -1.17
    VGA
    -1.16
     شوهر
    -1.16
    ISME
    -1.16
    loses
    -1.15
     dessas
    -1.15
    DAN
    -1.14
     sartén
    -1.13
    POSITIVE LOGITS
    They
    1.69
     about
    1.47
    眎
    1.34
     were
    1.26
     the
    1.25
    がない
    1.23
     condividere
    1.20
    Maße
    1.17
     verzichten
    1.16
     sentí
    1.15
    Activations Density 0.085%

    No Known Activations