© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 92620
    Prev
    Next
    INDEX
    Explanations

    request and response

    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
    iranje
    -0.86
     Dhabi
    -0.84
    Directed
    -0.82
    acken
    -0.81
    appBar
    -0.77
     Menü
    -0.76
     Kommune
    -0.75
    owaniu
    -0.75
     koning
    -0.75
     健康
    -0.75
    POSITIVE LOGITS
     response
    1.09
     await
    0.90
     of
    0.88
     responses
    0.85
     Envelope
    0.83
     réponse
    0.81
     void
    0.80
    Proyectos
    0.79
     Response
    0.79
    Respuesta
    0.79
    Activations Density 0.004%

    No Known Activations