© 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. 783
    Prev
    Next
    INDEX
    Explanations

    PostgreSQL database operations

    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
    those
    -1.58
    still
    -1.55
    times
    -1.53
    泐
    -1.47
     geha
    -1.42
     WHILE
    -1.41
    th
    -1.41
    킁
    -1.41
    mostly
    -1.38
    皤
    -1.35
    POSITIVE LOGITS
    ()
    1.47
     has
    1.44
     &&
    1.42
     about
    1.38
     Kerala
    1.38
     junho
    1.33
    žad
    1.30
    vosť
    1.29
     makes
    1.25
     gives
    1.25
    Activations Density 0.034%

    No Known Activations