© 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-16K
    7. 11578
    Prev
    Next
    INDEX
    Explanations

    primary or principal followed by key descriptor

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

    He first, vendor/

    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_16k_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
    ucha
    0.46
    बीर
    0.46
     透
    0.46
    吧
    0.46
    rok
    0.45
     सत्या
    0.45
    usi
    0.44
    amped
    0.44
    fea
    0.44
    透
    0.44
    POSITIVE LOGITS
     GSE
    0.47
     currencies
    0.46
     arrivals
    0.45
     biennium
    0.44
     Indic
    0.44
     adversaries
    0.44
     أنّ
    0.44
     الأوروب
    0.43
    களில்
    0.43
     حیر
    0.43
    Activations Density 0.016%

    No Known Activations