© 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. 149843
    Prev
    Next
    INDEX
    Explanations

    leave a comment

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

    influence these

    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
    <unused45>
    0.49
     በፊት
    0.47
    פו
    0.46
     occasioned
    0.46
     প্রাপ্য
    0.45
    עות
    0.45
     شكل
    0.43
    .".,
    0.43
    <unused46>
    0.43
    フォル
    0.43
    POSITIVE LOGITS
     a
    0.58
    a
    0.56
    SON
    0.55
     sa
    0.54
     指定
    0.51
     bane
    0.49
     aset
    0.49
    4
    0.49
    Hibernate
    0.49
     ny
    0.49
    Activations Density 0.000%

    No Known Activations