© 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. 663
    Prev
    Next
    INDEX
    Explanations

    AP followed by alphanumeric

    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
     —
    -2.94
    鯓
    -2.64
     могла
    -2.53
    狁
    -2.44
     fazia
    -2.44
     parecia
    -2.41
     consegui
    -2.33
    椟
    -2.30
     utilizzata
    -2.30
    ':
    -2.30
    POSITIVE LOGITS
    [
    3.08
     genannten
    2.84
    饪
    2.52
    ?
    2.44
    仍然
    2.44
    ing
    2.39
     resolves
    2.38
    巿
    2.34
    毋
    2.31
    B
    2.30
    Activations Density 0.013%

    No Known Activations