© 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. 209817
    Prev
    Next
    INDEX
    Explanations

    collocations and phrases

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

    models, Maximum, space, serialized, Israel

    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
     Zero
    0.46
     reconoc
    0.44
    0.44
     invis
    0.43
     [
    0.43
    ުރ
    0.42
    avras
    0.42
    2
    0.42
     è
    0.42
     Fix
    0.41
    POSITIVE LOGITS
    łu
    0.47
    কাহিনী
    0.47
    enseit
    0.45
     ನಗರ
    0.45
    ṯ
    0.45
    න්නේ
    0.44
    <unused95>
    0.44
     Staat
    0.44
    रिडोर
    0.44
    ího
    0.44
    Activations Density 0.000%

    No Known Activations