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. 38
    Prev
    Next
    INDEX
    Explanations

    random number generation

    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
    bellum
    -0.76
     纹理
    -0.74
     indicaciones
    -0.72
     olivia
    -0.71
     الجميع
    -0.70
     Maret
    -0.70
     jir
    -0.69
     interpret
    -0.69
     recruiters
    -0.68
     humanist
    -0.68
    POSITIVE LOGITS
    nacht
    0.89
    loyee
    0.85
     heilige
    0.85
    SafeMath
    0.85
    floor
    0.84
     roll
    0.84
    rona
    0.84
     referenties
    0.82
     number
    0.82
    ICom
    0.81
    Activations Density 0.019%

    No Known Activations