© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 54171
    Prev
    Next
    INDEX
    Explanations

    exit condition or error handling

    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
     Dax
    -0.72
    હે
    -0.69
     както
    -0.64
     Toen
    -0.64
     Nichts
    -0.63
     girlfriends
    -0.63
    Ago
    -0.62
    빨
    -0.62
     webpack
    -0.61
    結婚式
    -0.61
    POSITIVE LOGITS
    etano
    0.68
     audiencia
    0.67
     Lieu
    0.66
    ismus
    0.66
    加藤
    0.65
     retained
    0.65
     haystack
    0.65
     bodem
    0.65
    discipl
    0.64
    痊
    0.64
    Activations Density 0.043%

    No Known Activations