© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 12143
    Prev
    Next
    INDEX
    Explanations

    medical, technical, and descriptive terms

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

    labels or categories in lists of items, particularly in technical, medical, or classification contexts.

    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_22/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
     göm
    -1.43
     edades
    -1.38
     encender
    -1.38
     bebés
    -1.34
    okkal
    -1.34
     colgar
    -1.33
     például
    -1.32
    positionen
    -1.32
    씰
    -1.31
     notamment
    -1.30
    POSITIVE LOGITS
     at
    1.34
     during
    1.28
     not
    1.27
     after
    1.27
     as
    1.26
    すすめ
    1.23
     alongside
    1.22
     from
    1.17
     nestled
    1.16
     looked
    1.15
    Activations Density 0.054%

    No Known Activations