© 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. 101205
    Prev
    Next
    INDEX
    Explanations

    foreign words

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

    explaining templates and core ideas

    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
    DIFF
    0.47
    카
    0.45
     रिक्त
    0.45
     बढ़िया
    0.45
     ডিস
    0.44
     Ngo
    0.43
     Stip
    0.43
     Blak
    0.42
    displayName
    0.42
    addAttribute
    0.42
    POSITIVE LOGITS
     montagne
    0.48
    Heute
    0.48
     植物
    0.46
    л
    0.46
     seu
    0.45
    عت
    0.45
     fanno
    0.44
    etaan
    0.44
    ل
    0.44
    сми
    0.44
    Activations Density 0.000%

    No Known Activations