© 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. 56115
    Prev
    Next
    INDEX
    Explanations

    colors, shapes, and code syntax

    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
     úteis
    -0.85
    lcccc
    -0.82
    }{@
    -0.79
     высокая
    -0.77
    ENCODE
    -0.75
     from
    -0.75
     kū
    -0.74
    ␥
    -0.74
     вѣ
    -0.73
     Conférence
    -0.73
    POSITIVE LOGITS
    .\\
    1.05
    .
    0.89
    .}
    0.88
     TABLE
    0.82
    $^
    0.82
     algunos
    0.80
     |
    0.79
     referees
    0.77
    TABLE
    0.77
    0.76
    Activations Density 0.000%

    No Known Activations