© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 194681
    Prev
    Next
    INDEX
    Explanations

    computer, software, promo

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

    mathematics is the language

    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
    ল
    0.47
    is
    0.46
    ipo
    0.46
    (@
    0.45
     Divid
    0.44
    л
    0.44
    旯
    0.44
     Keb
    0.44
    arios
    0.43
    urah
    0.43
    POSITIVE LOGITS
     ተ
    0.58
     ഒരു
    0.55
     አንድ
    0.55
     වැඩි
    0.55
     މި
    0.55
     mathematician
    0.53
     mỗi
    0.52
     ಮತ್ತ
    0.51
     މަ
    0.51
     እ
    0.51
    Activations Density 0.000%

    No Known Activations