Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 7909
    Prev
    Next
    INDEX
    Explanations

    question, ASCII, code, or scan

    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
     stick
    -0.81
     Dokumentation
    -0.79
    正面
    -0.78
     briefing
    -0.78
     profile
    -0.77
    통
    -0.77
    gemene
    -0.77
     PLWABN
    -0.77
     България
    -0.75
    kript
    -0.75
    POSITIVE LOGITS
     scanned
    1.71
     digitized
    1.71
     scans
    1.50
     scan
    1.43
     Google
    1.38
    Scan
    1.36
    scan
    1.34
     OCR
    1.34
    Google
    1.31
     scanning
    1.27
    Activations Density 0.051%

    No Known Activations