© 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. 108457
    Prev
    Next
    INDEX
    Explanations

    abstract concepts and specific names

    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
     itinéraires
    -1.09
    спасибо
    -1.08
    lakukan
    -1.08
    matthew
    -1.04
    imágenes
    -1.04
    jeros
    -1.04
    bước
    -1.02
    koala
    -1.02
    olympic
    -1.02
    mitsubishi
    -1.01
    POSITIVE LOGITS
     preferable
    1.06
    我也不
    1.05
     consideration
    1.03
     functioning
    1.03
     tendency
    1.02
     utter
    1.01
     capability
    0.96
    jenih
    0.95
     начинает
    0.95
     conclusion
    0.95
    Activations Density 0.029%

    No Known Activations