© 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. 152712
    Prev
    Next
    INDEX
    Explanations

    people, couples, conference

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

    ** or**oroptions

    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
    顗
    0.49
    ಟ್ರ
    0.48
    ાદ
    0.48
    赳
    0.47
    乗り
    0.47
     Lehr
    0.46
     coi
    0.45
     Leach
    0.45
     Stark
    0.45
     ужа
    0.44
    POSITIVE LOGITS
         
    0.50
    :{
    0.47
    :
    0.47
               
    0.47
    ftl
    0.46
    ATION
    0.46
             
    0.46
    (|
    0.45
    :<
    0.44
    Paged
    0.44
    Activations Density 0.000%

    No Known Activations