© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108566
    Prev
    Next
    INDEX
    Explanations

    Joomla, Akeeba, Rox, news headlines

    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
     olsun
    -0.74
    🐆
    -0.73
     разли
    -0.70
    ाहरण
    -0.68
    淵
    -0.67
    ietal
    -0.66
    Lus
    -0.66
     Bush
    -0.65
    薇
    -0.64
     redo
    -0.63
    POSITIVE LOGITS
     Joomla
    1.75
    Jo
    1.30
    jo
    1.20
     jo
    1.13
     Jo
    1.05
    jom
    1.01
     Fabrik
    0.95
     Ake
    0.93
     sef
    0.93
    params
    0.92
    Activations Density 0.047%

    No Known Activations