© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 62795
    Prev
    Next
    INDEX
    Explanations

    reporting alleged events

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

    perceived exertion or seriousness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Areas
    0.46
    Suggestions
    0.46
    Observations
    0.46
    人員
    0.45
     Physiol
    0.44
    Responses
    0.44
     отмеча
    0.44
    ⌵
    0.44
    थरूम
    0.43
    MenuItems
    0.43
    POSITIVE LOGITS
    nominal
    0.50
    serious
    0.50
     ozbil
    0.47
     undisclosed
    0.46
     serious
    0.46
     timeframe
    0.46
     nominal
    0.46
     prefecture
    0.46
     অন্ধ
    0.45
     ),
    0.44
    Activations Density 0.000%

    No Known Activations