© 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. 32272
    Prev
    Next
    INDEX
    Explanations

    indicators and variables

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

    descriptive variable names

    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
    大
    0.66
    ।
    0.64
    Авто
    0.58
    ご
    0.55
    kingen
    0.54
    由
    0.53
     可
    0.53
    |-\
    0.53
    。
    0.53
    나
    0.53
    POSITIVE LOGITS
    指标
    0.71
     показатели
    0.65
     Indicators
    0.63
    指標
    0.61
    变量
    0.60
    indicators
    0.60
    Indicators
    0.59
     Variables
    0.57
     indicator
    0.56
     Metrics
    0.55
    Activations Density 0.010%

    No Known Activations