© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 149864
    Prev
    Next
    INDEX
    Explanations

    range and township

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

    SVG path data and coordinates

    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
    яс
    0.46
    另一个
    0.43
     النظر
    0.40
     ਹੋ
    0.40
    umsi
    0.39
     beyond
    0.39
     జ
    0.38
     ልጅ
    0.38
     স্র
    0.38
     போட்டு
    0.37
    POSITIVE LOGITS
    Cada
    0.46
    Тре
    0.43
    𝔹
    0.42
     rival
    0.40
    راه
    0.40
    Tomas
    0.40
    Как
    0.40
     Kare
    0.40
     Kada
    0.39
    MPS
    0.39
    Activations Density 0.001%

    No Known Activations