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. 8626
    Prev
    Next
    INDEX
    Explanations

    long-term, short-term, unclassified, peer review, medical records

    np_acts-logits-general · gemini-2.5-flash-lite

    phrases containing "long-term" and other adjective-noun combinations related to research objectives or document characteristics.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    different
    -1.37
    zzet
    -1.34
    都已经
    -1.30
    thirds
    -1.27
    fourths
    -1.26
     cán
    -1.24
     trhu
    -1.23
    others
    -1.20
     světě
    -1.18
     musst
    -1.17
    POSITIVE LOGITS
     wasn
    1.41
     continued
    1.40
     availability
    1.36
     approach
    1.31
     lack
    1.30
    2
    1.30
     resulting
    1.30
     aspect
    1.27
    ↵↵↵
    1.22
     didn
    1.21
    Activations Density 0.267%

    No Known Activations