© 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. 3039
    Prev
    Next
    INDEX
    Explanations

    states and statuses

    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
     būt
    -0.94
     durar
    -0.88
     ané
    -0.88
    lė
    -0.88
     requerido
    -0.88
    mė
    -0.85
     eivät
    -0.85
    Saluti
    -0.84
    eraard
    -0.83
     herre
    -0.82
    POSITIVE LOGITS
     list
    1.62
     ones
    1.60
    ness
    1.51
    list
    1.27
     count
    1.17
     projects
    1.16
     items
    1.16
     cases
    1.12
    Count
    1.11
     persons
    1.05
    Activations Density 0.075%

    No Known Activations