© 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. 38523
    Prev
    Next
    INDEX
    Explanations

    numbers and ranges

    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
     gamme
    -0.77
    nament
    -0.74
     silueta
    -0.74
    diagnostic
    -0.73
     voyageurs
    -0.72
     Mathi
    -0.71
     dota
    -0.70
    학
    -0.70
    処理
    -0.69
    YI
    -0.68
    POSITIVE LOGITS
     vývoj
    0.70
     extiende
    0.66
     padrão
    0.65
     בב
    0.65
     Categories
    0.64
    SelectAll
    0.64
    ults
    0.64
     sullo
    0.63
    till
    0.63
     ability
    0.61
    Activations Density 0.045%

    No Known Activations