© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 154996
    Prev
    Next
    INDEX
    Explanations

    individual gifts

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

    selecting Generator Build

    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
    닷
    0.46
    บาย
    0.42
     مباشرة
    0.41
     recre
    0.41
    Elim
    0.40
     combate
    0.40
     conden
    0.40
    더라
    0.40
     spitting
    0.40
    코
    0.40
    POSITIVE LOGITS
     Selecting
    0.57
     ও
    0.53
     và
    0.52
    ucksack
    0.50
     और
    0.48
     Standardization
    0.48
     අවශ්‍ය
    0.48
    和小
    0.48
     és
    0.47
     και
    0.47
    Activations Density 0.000%

    No Known Activations