© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 38103
    Prev
    Next
    INDEX
    Explanations

    questions, validity, AI research

    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
     Campe
    -0.77
     ENO
    -0.73
    Campe
    -0.73
    Paola
    -0.71
    JU
    -0.70
    bani
    -0.70
     նաև
    -0.70
    lassification
    -0.68
    inderella
    -0.67
    jef
    -0.67
    POSITIVE LOGITS
    balloon
    0.90
     balloons
    0.88
     balloon
    0.79
     Inflation
    0.77
     Beloved
    0.77
     Remains
    0.77
     voltaje
    0.76
     лен
    0.75
    codings
    0.75
     MILITARY
    0.75
    Activations Density 0.012%

    No Known Activations