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. 45
    Prev
    Next
    INDEX
    Explanations

    pass or skipping

    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
     tè
    -0.91
     เล
    -0.91
     yake
    -0.87
     elektronik
    -0.85
     گیری
    -0.85
     travel
    -0.85
    goto
    -0.85
     เจ
    -0.85
    hasta
    -0.85
     sete
    -0.85
    POSITIVE LOGITS
     by
    1.63
     Passing
    1.46
     pass
    1.42
     through
    1.37
     passes
    1.30
    Pass
    1.29
     Pass
    1.29
     passing
    1.29
     from
    1.24
    passing
    1.23
    Activations Density 0.004%

    No Known Activations