© 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. 93952
    Prev
    Next
    INDEX
    Explanations

    keywords and identifiers

    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
     guia
    -0.72
     comming
    -0.70
    EO
    -0.67
    ssch
    -0.66
    atine
    -0.65
    sworth
    -0.65
    wellen
    -0.65
    codecs
    -0.65
    aterial
    -0.63
    òria
    -0.63
    POSITIVE LOGITS
     Sarko
    0.77
     リボン
    0.76
     HAT
    0.71
    годно
    0.70
    crivez
    0.67
    isc
    0.67
     Sax
    0.66
    Topics
    0.66
    の見
    0.66
     Vertex
    0.65
    Activations Density 0.061%

    No Known Activations