© 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. 10649
    Prev
    Next
    INDEX
    Explanations

    My followed by a noun

    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
     are
    -2.20
    一直
    -2.17
    要
    -2.16
    ,"
    -2.08
    賔
    -2.06
     рекомендуется
    -2.05
    🫶
    -1.96
    䊐
    -1.96
    corrhi
    -1.95
    杙
    -1.95
    POSITIVE LOGITS
    ’
    2.53
    一旁
    2.39
     Our
    2.30
     genaue
    2.23
     kurze
    2.13
     ‘
    2.13
     schlechte
    2.08
     “(
    2.05
     撮っ
    1.98
    這麼
    1.98
    Activations Density 0.024%

    No Known Activations