© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 23745
    Prev
    Next
    INDEX
    Explanations

    title case headings

    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
    boll
    -0.73
     online
    -0.72
    ള
    -0.71
     Landschaft
    -0.69
     Please
    -0.66
    станов
    -0.66
     harapan
    -0.66
     امکان
    -0.66
     PLoS
    -0.65
    ]+$
    -0.65
    POSITIVE LOGITS
     doctrine
    1.03
    timate
    0.91
    stripped
    0.88
     manuals
    0.87
     doctrinal
    0.85
     Doctrine
    0.85
     која
    0.84
     Jume
    0.82
    timately
    0.80
     drills
    0.80
    Activations Density 0.011%

    No Known Activations