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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 78794
    Prev
    Next
    INDEX
    Explanations

    business, task, point, result, time

    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
     طالب
    -0.79
    deki
    -0.79
     alc
    -0.78
     ********
    -0.78
     畫
    -0.78
     "-",
    -0.78
     spanish
    -0.78
    isEnabled
    -0.76
    這是
    -0.76
     ".",
    -0.76
    POSITIVE LOGITS
    Ễ
    1.00
    menuhi
    0.99
    って何
    0.94
    доволь
    0.94
     أس
    0.89
     aplicativo
    0.89
     retorna
    0.87
    bata
    0.86
     llega
    0.85
    ftal
    0.85
    Activations Density 0.586%

    No Known Activations