© 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. 90922
    Prev
    Next
    INDEX
    Explanations

    names starting with A followed by a vowel

    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
     trọng
    -0.81
    ليم
    -0.77
     incrust
    -0.76
    divarius
    -0.75
     гар
    -0.71
    θηκε
    -0.71
     nostre
    -0.71
     則
    -0.70
    teck
    -0.70
     better
    -0.68
    POSITIVE LOGITS
    的情況
    0.77
    rister
    0.76
     cadena
    0.74
     VICT
    0.71
     coisa
    0.71
    ██
    0.70
     Therm
    0.70
    stairs
    0.69
     Ciencia
    0.69
     Kabupaten
    0.69
    Activations Density 0.025%

    No Known Activations