© 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. 195217
    Prev
    Next
    INDEX
    Explanations

    specifying intent or reason

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

    specifically designed

    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
     any
    0.47
    nd
    0.47
     efficiency
    0.44
    ച്ചത്
    0.44
     ONLY
    0.44
     SERIES
    0.44
    {
    0.43
    💧
    0.42
    names
    0.42
     ANYTHING
    0.41
    POSITIVE LOGITS
     Verfü
    0.49
    ümüz
    0.48
     специально
    0.47
    सेवी
    0.46
    வர்க
    0.45
    ürich
    0.45
    стого
    0.42
     Миха
    0.42
     zwró
    0.42
     Mục
    0.42
    Activations Density 0.002%

    No Known Activations