© 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. 199357
    Prev
    Next
    INDEX
    Explanations

    ambassador, activities, EC, why

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

    how many, forgotten laundromat, 'K'

    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
     божомолу
    0.65
     공연
    0.57
     理解
    0.51
     मार्ग
    0.50
     肌
    0.50
     谢
    0.50
     书
    0.49
     PhoneNumber
    0.49
     منسل
    0.48
     第
    0.48
    POSITIVE LOGITS
    at
    0.54
    ی
    0.52
    in
    0.50
     setores
    0.48
     Revolt
    0.47
     establish
    0.47
     names
    0.47
     habitants
    0.46
     and
    0.46
    character
    0.46
    Activations Density 0.000%

    No Known Activations