© 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. 143385
    Prev
    Next
    INDEX
    Explanations

    business, engineering, and concepts

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

    time limits or duration

    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
    s
    0.62
    తారు
    0.44
    muted
    0.43
    sion
    0.42
     supaya
    0.42
    ten
    0.41
    ographic
    0.41
    sides
    0.41
    ating
    0.41
    gre
    0.40
    POSITIVE LOGITS
    起動
    0.51
     單
    0.50
    컨
    0.48
    \}
    0.48
    畢業
    0.48
    的情況
    0.48
    ᄐ
    0.48
     親
    0.47
    驕
    0.47
     consape
    0.47
    Activations Density 0.000%

    No Known Activations