© 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. 38179
    Prev
    Next
    INDEX
    Explanations

    Newborn photography, health, and lifestyle

    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
     idag
    -0.85
    TRON
    -0.77
     Engr
    -0.76
    cules
    -0.75
    $[\
    -0.75
    TextBox
    -0.75
    ☆☆☆☆☆
    -0.75
     delegado
    -0.74
     péché
    -0.73
     tissus
    -0.73
    POSITIVE LOGITS
     Vertrags
    0.90
     Thursday
    0.81
    Ssl
    0.79
     semifinals
    0.79
     insofar
    0.79
    もあって
    0.78
     Inhalte
    0.77
    endiri
    0.77
    も多く
    0.77
     termini
    0.76
    Activations Density 0.000%

    No Known Activations