© 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. 158912
    Prev
    Next
    INDEX
    Explanations

    people's roles and qualities

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

    lights flicker

    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
    PIL
    0.49
    ொ
    0.49
    ӑ
    0.46
    꽂
    0.46
    🚵
    0.46
    或
    0.46
    批量
    0.44
    ⟣
    0.44
    ⎯
    0.44
    Το
    0.43
    POSITIVE LOGITS
     superstars
    0.55
     manly
    0.54
     entertainer
    0.52
     trener
    0.51
     playmaker
    0.51
     stars
    0.51
     estrellas
    0.51
     Cnemidophorus
    0.51
     giocatori
    0.51
     supporters
    0.50
    Activations Density 0.000%

    No Known Activations