© 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. 44834
    Prev
    Next
    INDEX
    Explanations

    tokens followed by punctuation

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

    commas and dashes

    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
    ди
    0.50
    مكن
    0.46
    めでとう
    0.45
    ნი
    0.43
    ણે
    0.42
    scoring
    0.42
    ディ
    0.42
    𝘦
    0.42
    difficult
    0.42
    敬
    0.41
    POSITIVE LOGITS
     Gelände
    0.54
     ఏర్ప
    0.50
     মোহ
    0.47
     दरअसल
    0.46
     silo
    0.45
     ఎమ్మె
    0.45
     المرحله
    0.44
     سوا
    0.43
     sentimos
    0.43
     Unilever
    0.43
    Activations Density 0.000%

    No Known Activations