© 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. 592
    Prev
    Next
    INDEX
    Explanations

    Dennis followed by a surname

    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
    軚
    -3.03
    锴
    -2.95
     tématu
    -2.80
    怍
    -2.78
    劼
    -2.67
     делает
    -2.63
    螂
    -2.61
    渽
    -2.56
     программа
    -2.53
     baterie
    -2.53
    POSITIVE LOGITS
    2
    3.56
    9
    3.11
    -
    2.84
    6
    2.81
    7
    2.77
    to
    2.73
    le
    2.69
    This
    2.64
    1
    2.63
     lia
    2.50
    Activations Density 0.004%

    No Known Activations