© 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. 221298
    Prev
    Next
    INDEX
    Explanations

    Carrie Underwood tickets

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

    bypass authentication bottlenecks

    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
    allaitement
    0.50
    結婚
    0.48
    妊娠
    0.48
     }^{*}$
    0.46
    ۲۰
    0.46
    ੳ
    0.45
    éto
    0.45
    ૬
    0.45
    घा
    0.45
    น
    0.45
    POSITIVE LOGITS
     pry
    0.44
     NAACP
    0.44
     Trouble
    0.44
     Presumably
    0.44
     artillery
    0.43
    vors
    0.42
     magasin
    0.42
     Stewart
    0.41
     Pflanzen
    0.41
     J
    0.41
    Activations Density 0.001%

    No Known Activations