© 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. 78301
    Prev
    Next
    INDEX
    Explanations

    averages and percentages

    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
    Ute
    -0.82
    ctober
    -0.81
     latter
    -0.80
     inaprop
    -0.80
    ategori
    -0.79
     prv
    -0.78
    illets
    -0.77
    elp
    -0.77
     kind
    -0.75
    pFile
    -0.75
    POSITIVE LOGITS
    avg
    1.01
     avg
    1.00
    Average
    0.96
    Avg
    0.88
     averaging
    0.87
    verages
    0.84
    want
    0.83
    yes
    0.83
     average
    0.82
    入
    0.82
    Activations Density 0.018%

    No Known Activations