© 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. 213442
    Prev
    Next
    INDEX
    Explanations

    cause more

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

    listing or bullet points

    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
    Negative Logits
    稱
    0.45
     ঝুঁ
    0.43
     використо
    0.42
     இணைந்து
    0.42
     அமைக்க
    0.42
     മാറ്റ
    0.42
    RNN
    0.42
    磵
    0.42
    痫
    0.41
     difficoltà
    0.41
    POSITIVE LOGITS
    </h2>
    0.44
     Because
    0.43
    <eos>
    0.41
    ↵↵↵
    0.41
     Already
    0.40
     corners
    0.40
     wanton
    0.40
    ↵↵
    0.39
     Though
    0.39
     bund
    0.39
    Activations Density 0.000%

    No Known Activations