© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64438
    Prev
    Next
    INDEX
    Explanations

    numbers and commas

    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
    ayangkan
    -0.85
     など
    -0.84
     nostalgic
    -0.84
    Ｘ
    -0.83
     quinta
    -0.80
    łami
    -0.79
    视着
    -0.78
    远处
    -0.78
    极了
    -0.77
    मत
    -0.77
    POSITIVE LOGITS
     soggior
    0.86
     
    0.85
     requerida
    0.81
     бюдже
    0.81
     baden
    0.80
    ajinan
    0.79
     ligt
    0.78
    bericht
    0.78
    ţei
    0.78
     telt
    0.77
    Activations Density 0.123%

    No Known Activations