© 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. 115739
    Prev
    Next
    INDEX
    Explanations

    "on Your Website" or "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_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
    intenant
    -0.69
    Livre
    -0.67
    parentId
    -0.65
     Irene
    -0.64
     Olivia
    -0.64
     technical
    -0.64
     adults
    -0.63
     traumas
    -0.63
     spese
    -0.61
     founder
    -0.60
    POSITIVE LOGITS
    PLANATION
    0.79
    utado
    0.73
     Franch
    0.70
     مناف
    0.68
    ooooooo
    0.68
    wet
    0.68
     Рей
    0.68
    CHEZ
    0.67
     swallowed
    0.67
    amic
    0.67
    Activations Density 0.210%

    No Known Activations