© 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. 228319
    Prev
    Next
    INDEX
    Explanations

    form within, fall shares, key employees, deformed singer

    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
     Grammar
    0.55
     grammar
    0.53
    directed
    0.47
     directed
    0.46
    '
    0.46
     vocabulary
    0.46
    ape
    0.46
    きの
    0.44
     terminology
    0.44
    .
    0.43
    POSITIVE LOGITS
     হেন
    0.53
     GDPPC
    0.49
     গর্
    0.49
     தோன்ற
    0.48
     ব্যাব
    0.48
     আভ্যন্তরীণ
    0.48
     RBC
    0.47
     اوم
    0.47
     MANAG
    0.47
     RBS
    0.46
    Activations Density 0.001%

    No Known Activations