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. 8070
    Prev
    Next
    INDEX
    Explanations

    entry categories and classified places

    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
     those
    -1.27
     some
    -1.20
     during
    -1.14
     many
    -1.09
     did
    -1.08
     any
    -1.08
     both
    -1.06
     seemingly
    -1.01
     countless
    -1.00
     before
    -0.98
    POSITIVE LOGITS
     шабло
    1.27
     Wikimedia
    1.23
     soportes
    1.09
    覷
    1.09
     parámetros
    1.06
     لهذه
    1.06
    wikipedia
    1.05
     wiki
    1.05
     magnifiques
    1.05
     rác
    1.05
    Activations Density 0.009%

    No Known Activations