© 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. 20850
    Prev
    Next
    INDEX
    Explanations

    exclamatory phrases at start of sentences

    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
     it
    -1.92
     you
    -1.81
     mesma
    -1.52
     cadeira
    -1.34
    その時
    -1.30
     mesmos
    -1.27
    ைய
    -1.23
    ApJ
    -1.23
    licado
    -1.23
     做
    -1.21
    POSITIVE LOGITS
    .“
    1.55
    ksesta
    1.49
     особенно
    1.48
     jaunes
    1.47
    ｘ
    1.27
     حتی
    1.22
    UNIDAD
    1.20
    </strong>
    1.20
     useAppContext
    1.20
     amélior
    1.20
    Activations Density 0.018%

    No Known Activations