© 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. 75824
    Prev
    Next
    INDEX
    Explanations

    technical image indicators

    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
     ané
    -0.81
     cuer
    -0.79
    melada
    -0.79
     numeros
    -0.77
    vode
    -0.76
     explanation
    -0.76
     vano
    -0.76
     interi
    -0.75
     ایم
    -0.75
     Asie
    -0.75
    POSITIVE LOGITS
    чины
    0.78
    ты
    0.78
     sheath
    0.77
    скую
    0.75
     PLE
    0.75
     съдържа
    0.74
    enery
    0.73
    ādā
    0.71
     ultrason
    0.71
    南北
    0.71
    Activations Density 0.006%

    No Known Activations