© 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. 81555
    Prev
    Next
    INDEX
    Explanations

    city in

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

    discussing what's new

    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
    ⁺
    0.44
     ACS
    0.42
     Transient
    0.41
    CREATED
    0.40
    м
    0.40
    器件
    0.40
     penta
    0.39
    °
    0.39
     этих
    0.38
     Each
    0.38
    POSITIVE LOGITS
     ولا
    0.50
    government
    0.48
     filosofía
    0.48
     willkommen
    0.48
    revista
    0.48
     سوشل
    0.48
     شاید
    0.47
     براي
    0.45
     milyon
    0.45
     ایل
    0.45
    Activations Density 0.003%

    No Known Activations