© 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. 10-GEMMASCOPE-RES-131K
    7. 90356
    Prev
    Next
    INDEX
    Explanations

    US auto, similar content, Q:

    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_10/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
     schlechte
    -1.74
     歳
    -1.69
     schwere
    -1.68
     actually
    -1.65
     espectáculos
    -1.63
     contactar
    -1.60
     steder
    -1.57
     soportes
    -1.53
     grossa
    -1.53
     supaya
    -1.53
    POSITIVE LOGITS
     to
    2.30
     for
    1.96
     of
    1.74
    <bos>
    1.69
    ⑊
    1.58
    both
    1.53
                   
    1.52
    (\
    1.47
     sowohl
    1.45
     quell
    1.44
    Activations Density 0.002%

    No Known Activations