© 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. 77121
    Prev
    Next
    INDEX
    Explanations

    boost.org links

    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
    岡
    -0.85
     Video
    -0.70
     Experiment
    -0.70
    Video
    -0.69
    Experiment
    -0.69
    crates
    -0.69
     horloge
    -0.68
     fotográfico
    -0.68
    urized
    -0.67
    allo
    -0.65
    POSITIVE LOGITS
     Mädchen
    0.75
     sva
    0.73
    階級
    0.68
    trice
    0.66
    seit
    0.65
    rosio
    0.65
    inicio
    0.64
     ответа
    0.63
    txtName
    0.63
     mardi
    0.62
    Activations Density 0.060%

    No Known Activations