© 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. 77153
    Prev
    Next
    INDEX
    Explanations

    available upon request

    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
    intended
    -0.88
     asio
    -0.80
     ambul
    -0.80
     exercice
    -0.77
     augmenté
    -0.77
    expected
    -0.76
     tenter
    -0.76
     RESTRICT
    -0.75
     Intended
    -0.75
     affichés
    -0.74
    POSITIVE LOGITS
     request
    5.03
    request
    3.56
     requests
    2.84
     Request
    2.78
    REQUEST
    2.69
     recommendation
    2.69
    Request
    2.66
     suggestion
    2.63
     invitation
    2.58
     REQUEST
    2.52
    Activations Density 0.085%

    No Known Activations