© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 106306
    Prev
    Next
    INDEX
    Explanations

    code snippets and structured data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    𝑨
    -0.71
    vings
    -0.71
    xia
    -0.71
     hex
    -0.69
    zki
    -0.67
     Hose
    -0.66
     parts
    -0.66
    tier
    -0.66
     identification
    -0.65
     disp
    -0.65
    POSITIVE LOGITS
    حاد
    0.78
    UserRepository
    0.67
    ConfigService
    0.64
    guint
    0.63
    systemctl
    0.63
     Autres
    0.63
    رش
    0.62
    şk
    0.62
    PROF
    0.61
    逃げ
    0.61
    Activations Density 0.089%

    No Known Activations