© 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. 92274
    Prev
    Next
    INDEX
    Explanations

    html data attributes

    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
     devuelve
    -1.00
     mutfak
    -0.99
     voldoende
    -0.95
    vių
    -0.93
    ctiv
    -0.92
    uatu
    -0.90
    仨
    -0.89
     daarom
    -0.89
     zoveel
    -0.88
    おそ
    -0.88
    POSITIVE LOGITS
     their
    1.31
     both
    1.06
     those
    1.04
     despite
    0.95
     by
    0.95
     just
    0.94
     aikana
    0.93
     hellen
    0.93
     then
    0.93
     its
    0.92
    Activations Density 0.010%

    No Known Activations