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. 8239
    Prev
    Next
    INDEX
    Explanations

    code identifiers and assignments

    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
     this
    -1.88
     which
    -1.67
     what
    -1.63
     huge
    -1.57
     supremely
    -1.55
     drastically
    -1.55
     oddly
    -1.53
     horribly
    -1.53
     both
    -1.51
     sophisticated
    -1.51
    POSITIVE LOGITS
    particularly
    1.45
     همچنین
    1.34
    もある
    1.32
     malgré
    1.30
    があった
    1.27
     acclaimed
    1.26
    despite
    1.26
     praktisch
    1.26
    などは
    1.26
    makes
    1.25
    Activations Density 0.029%

    No Known Activations