© 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. 185624
    Prev
    Next
    INDEX
    Explanations

    change this

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

    actions, consequences, or outcomes

    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
    স্ম
    0.44
    <unused21>
    0.43
    มัน
    0.43
    ბ
    0.41
    ਬ
    0.41
    适
    0.41
    ंपेक्षा
    0.39
    喜び
    0.39
    并非
    0.39
    替代
    0.39
    POSITIVE LOGITS
     jour
    0.53
     fateful
    0.50
     identificado
    0.50
     journe
    0.50
     probabil
    0.49
    ços
    0.48
     building
    0.48
     を
    0.47
     propyl
    0.47
    ी
    0.47
    Activations Density 0.000%

    No Known Activations