© 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. 118589
    Prev
    Next
    INDEX
    Explanations

    redistribute, modification, sell-off, permission

    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
    dios
    -0.75
    adrez
    -0.74
    谛
    -0.73
    锑
    -0.70
    entikan
    -0.69
    熱
    -0.69
    dă
    -0.69
    通りの
    -0.68
    ناول
    -0.68
    ítő
    -0.68
    POSITIVE LOGITS
    CTC
    0.71
    Bueno
    0.68
    只好
    0.66
    сказа
    0.64
    imple
    0.64
     رش
    0.63
     doğal
    0.63
    Cairo
    0.63
    tab
    0.63
    xel
    0.63
    Activations Density 0.057%

    No Known Activations