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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8000
    Prev
    Next
    INDEX
    Explanations

    game scores and outcomes

    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
     Bestimmungen
    -0.90
     inasmuch
    -0.90
    Nej
    -0.87
    olism
    -0.86
     Geset
    -0.85
     усі
    -0.85
    Aktualisiert
    -0.84
    Bereich
    -0.83
     aggrieved
    -0.82
     várias
    -0.82
    POSITIVE LOGITS
     “[
    0.91
     payed
    0.88
    身旁
    0.85
     essi
    0.83
     speculations
    0.82
    看见
    0.82
     commentators
    0.81
    pastebin
    0.81
    umé
    0.81
     带
    0.80
    Activations Density 0.099%

    No Known Activations