© 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. 1594
    Prev
    Next
    INDEX
    Explanations

    mosaic

    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
     Sede
    -0.75
    甲
    -0.74
    RequestBody
    -0.69
    صیلات
    -0.68
     Obra
    -0.68
    renal
    -0.67
    engines
    -0.67
    Ր
    -0.66
     kanker
    -0.66
    registry
    -0.66
    POSITIVE LOGITS
     mosaics
    1.59
     mosaic
    1.50
    mosa
    1.31
    mosaic
    1.12
    Mosaic
    0.97
     Mosaic
    0.97
     moza
    0.89
     mosa
    0.85
     Trier
    0.84
    Mosa
    0.81
    Activations Density 0.023%

    No Known Activations