© 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. 34-GEMMASCOPE-RES-131K
    7. 109779
    Prev
    Next
    INDEX
    Explanations

    release notes

    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_34/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
    üns
    -0.75
    avyzd
    -0.73
     furnishing
    -0.72
     تعريف
    -0.72
    ӹ
    -0.71
     einsetzen
    -0.71
    гава
    -0.69
     κάπο
    -0.68
    FrameLayout
    -0.68
    MenuView
    -0.68
    POSITIVE LOGITS
     changelog
    2.91
     changes
    2.50
    Changelog
    2.28
    changelog
    2.25
     Changes
    2.20
     Changelog
    2.13
    changes
    2.11
    Changes
    2.05
     CHANGES
    2.02
     release
    2.00
    Activations Density 0.103%

    No Known Activations