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. 8632
    Prev
    Next
    INDEX
    Explanations

    temporal kinetics, variety of applications

    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
     tüm
    -0.82
     pelbagai
    -0.81
     formato
    -0.81
    immutable
    -0.80
     Ratings
    -0.80
     motivadoras
    -0.80
     liczba
    -0.80
     desmotiv
    -0.79
    书法
    -0.79
     doença
    -0.78
    POSITIVE LOGITS
     ſtre
    1.00
    zembro
    0.99
    ANSION
    0.93
    ressor
    0.92
    ifrance
    0.88
    PARATUS
    0.87
    Carthy
    0.87
     القدس
    0.87
    ksjon
    0.86
     производится
    0.86
    Activations Density 0.000%

    No Known Activations