© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 109907
    Prev
    Next
    INDEX
    Explanations

    L words and specific endings

    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
    esses
    -0.99
    ختی
    -0.81
     puri
    -0.80
    ORAGE
    -0.72
    Ė
    -0.70
    rage
    -0.69
    Posts
    -0.69
     Gara
    -0.68
     Elephants
    -0.68
    大战
    -0.66
    POSITIVE LOGITS
     khán
    0.78
    esseur
    0.75
    λλη
    0.74
     softmax
    0.74
    下車
    0.73
     veterinarian
    0.73
    ācija
    0.73
    Wolfgang
    0.72
     FORECAST
    0.71
     dzieci
    0.71
    Activations Density 0.020%

    No Known Activations