© 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. 28166
    Prev
    Next
    INDEX
    Explanations

    time or life

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

    Disco Elysium

    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
    m
    0.66
    r
    0.58
    j
    0.53
    let
    0.53
    five
    0.52
    f
    0.52
    arr
    0.51
    money
    0.51
    net
    0.50
    lor
    0.50
    POSITIVE LOGITS
    晧
    0.55
     antérieurs
    0.52
    ження
    0.50
    禣
    0.50
     desempenho
    0.49
    ੦
    0.49
    葢
    0.49
     exposição
    0.48
     tragic
    0.48
     preparação
    0.48
    Activations Density 0.000%

    No Known Activations