© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 101353
    Prev
    Next
    INDEX
    Explanations

    KeyEvent or MouseEvent activations

    np_acts-logits-general · gemini-2.5-flash-lite

    references to event-related programming objects and classes, particularly in GUI or event-driven systems.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
    m
    -4.03
    or
    -2.72
    f
    -2.67
    at
    -2.61
    h
    -2.52
    right
    -2.47
    脔
    -2.45
    ed
    -2.44
    ]
    -2.39
    o
    -2.38
    POSITIVE LOGITS
     gewiß
    2.78
    犼
    2.39
    tedì
    2.33
    ޒ
    2.28
     betyr
    2.28
     огромное
    2.25
     olvidado
    2.22
    anyeol
    2.22
    zmm
    2.20
    ſu
    2.20
    Activations Density 0.002%

    No Known Activations