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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 599
    Prev
    Next
    INDEX
    Explanations

    dk and gb country codes

    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
    镦
    -3.16
    嗞
    -3.06
    葙
    -2.89
    pecabe
    -2.88
    🢒
    -2.58
    蹋
    -2.50
    咴
    -2.50
    ’).
    -2.50
    י
    -2.45
    messung
    -2.39
    POSITIVE LOGITS
    2
    3.70
    en
    3.27
    1
    3.23
    (
    3.22
    /
    3.20
    “
    3.02
    3
    2.91
    ––
    2.88
    I
    2.84
    ",
    2.78
    Activations Density 0.003%

    No Known Activations