© 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. 75459
    Prev
    Next
    INDEX
    Explanations

    suggesting or opposing actions

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

    multiple languages or concepts

    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
    _
    0.51
     in
    0.46
     fe
    0.44
     performance
    0.41
    ird
    0.41
     North
    0.40
     tackle
    0.40
     display
    0.39
     confronted
    0.39
     treating
    0.38
    POSITIVE LOGITS
    espèce
    0.59
    წიფ
    0.59
    sous
    0.58
    sama
    0.55
    asparagus
    0.53
     ಯೋಜ
    0.52
     jambes
    0.52
    鮋
    0.52
    friends
    0.51
     déjeuner
    0.51
    Activations Density 0.000%

    No Known Activations