© 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. 47839
    Prev
    Next
    INDEX
    Explanations

    foreign language or technical terms

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

    extracting files, parallel strings, metadata changes, small files

    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
    floral
    0.53
    Floral
    0.50
    kaj
    0.48
    กก
    0.48
    👪
    0.47
    től
    0.46
    Tissue
    0.46
    術
    0.46
    ้ว
    0.45
    ก
    0.45
    POSITIVE LOGITS
     blinked
    0.44
     sorely
    0.39
     اشت
    0.39
     wronged
    0.38
    creto
    0.38
     hammered
    0.38
     حالة
    0.38
     troublesome
    0.37
     이루
    0.36
     langu
    0.36
    Activations Density 0.000%

    No Known Activations