© 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. 209840
    Prev
    Next
    INDEX
    Explanations

    names and titles

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

    before grilling, kosher salt

    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
     compelling
    0.50
    シフト
    0.47
    ետ
    0.47
    柔
    0.46
    ёт
    0.45
     sozial
    0.45
    डी
    0.45
    髭
    0.45
    バン
    0.44
    गेन
    0.44
    POSITIVE LOGITS
     Observed
    0.48
     poderá
    0.45
     Parties
    0.45
    --->
    0.44
     Pins
    0.43
    
    0.43
    -->
    0.42
     يبقى
    0.42
     القب
    0.42
    يبقى
    0.41
    Activations Density 0.000%

    No Known Activations