© 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. 10-GEMMASCOPE-RES-131K
    4. 70471
    Prev
    Next
    INDEX
    Explanations

    Javier Velázquez, Road Trip, Our Difference

    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_10/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
    几人
    -1.60
     galima
    -1.55
     comienzan
    -1.50
     rése
    -1.47
     cheio
    -1.44
    begins
    -1.42
     desarrollando
    -1.42
    衄
    -1.41
     Announces
    -1.41
    lamabad
    -1.38
    POSITIVE LOGITS
     are
    1.94
    There
    1.84
     on
    1.82
    This
    1.76
     This
    1.75
    These
    1.74
     Since
    1.70
    .
    1.70
     should
    1.67
     Unfortunately
    1.63
    Activations Density 0.001%

    No Known Activations