© 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. 58841
    Prev
    Next
    INDEX
    Explanations

    panels and fixing

    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
     prestar
    -0.78
    ]^{-
    -0.75
    prior
    -0.75
    laub
    -0.70
    轮
    -0.69
    ppt
    -0.68
    decorators
    -0.67
    霸王
    -0.67
     }_{
    -0.67
    getDrawable
    -0.67
    POSITIVE LOGITS
     pan
    4.38
     Pan
    4.00
    Pan
    3.97
    pan
    3.75
     PAN
    3.69
     panel
    3.56
    PAN
    3.56
     panels
    3.30
     пан
    3.19
     Panthers
    3.11
    Activations Density 0.031%

    No Known Activations