© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 47266
    Prev
    Next
    INDEX
    Explanations

    social events or sport

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

    foundation and building

    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
     フォト
    0.53
     ಸಮಸ್ಯೆ
    0.53
    '_{
    0.52
    todos
    0.50
    ept
    0.50
    беріга
    0.50
    \|+\
    0.50
    eppo
    0.50
    ங்கிணை
    0.49
     ね
    0.49
    POSITIVE LOGITS
     launch
    0.55
    Launch
    0.48
    Medium
    0.48
     mediums
    0.46
     loop
    0.45
    Industry
    0.45
     medium
    0.43
     Launch
    0.43
     hours
    0.43
     بدء
    0.42
    Activations Density 0.000%

    No Known Activations