© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77457
    Prev
    Next
    INDEX
    Explanations

    regulatory bodies, prices, utilities

    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
    Not in Any Lists

    No Comments

    Negative Logits
     überweisen
    -0.79
     Verlust
    -0.78
    dańsk
    -0.73
    痕迹
    -0.71
    ଦ
    -0.70
    ymas
    -0.68
     Betrieb
    -0.68
    Chop
    -0.68
    Without
    -0.68
     loss
    -0.68
    POSITIVE LOGITS
     shareholders
    0.79
    $^{\
    0.77
    Planner
    0.76
    慾
    0.76
     Avian
    0.75
    '\\
    0.72
     نقل
    0.71
    OPT
    0.70
     -:
    0.70
    梦见
    0.70
    Activations Density 0.023%

    No Known Activations