© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 218190
    Prev
    Next
    INDEX
    Explanations

    then they, guarantees because, begins before

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

    hypothetical questions and explanations

    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
    trainer
    0.49
    d
    0.47
    nasa
    0.46
    mvc
    0.46
    receiver
    0.44
    j
    0.43
    snippet
    0.43
    a
    0.43
    akse
    0.42
    dancer
    0.42
    POSITIVE LOGITS
     সমস্যার
    0.49
     croissance
    0.49
     предостав
    0.49
     investigação
    0.49
     ಕಳೆದ
    0.47
     ridiculed
    0.46
    <unused534>
    0.46
    ியுள்ள
    0.46
     pied
    0.46
    !";
    0.46
    Activations Density 0.000%

    No Known Activations