© 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. 167874
    Prev
    Next
    INDEX
    Explanations

    review products or services to earn

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

    lists of items or descriptions

    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
    सम
    0.46
     กร
    0.46
     Currently
    0.46
    ं
    0.46
     이해
    0.45
     Endgame
    0.45
     Through
    0.45
     Because
    0.45
     Understanding
    0.44
     Overwatch
    0.44
    POSITIVE LOGITS
    ан
    0.50
    circa
    0.47
    angwa
    0.46
    ari
    0.46
    ő
    0.46
    ន់
    0.45
    orul
    0.45
     azúcar
    0.44
    buri
    0.44
    мий
    0.44
    Activations Density 0.001%

    No Known Activations