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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 61337
    Prev
    Next
    INDEX
    Explanations

    biological function and impact

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

    verbs that indicate causal relationships or mechanisms in scientific literature.

    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_10/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
     dôle
    -1.52
     potrebné
    -1.50
     každý
    -1.38
     съдържа
    -1.38
     dobrý
    -1.37
     stále
    -1.34
     nový
    -1.34
     męski
    -1.33
     Ответить
    -1.33
    vides
    -1.31
    POSITIVE LOGITS
     we
    1.48
     regarding
    1.47
     by
    1.46
     Our
    1.44
     first
    1.40
     quite
    1.38
     very
    1.35
    ?).
    1.34
    خرى
    1.34
     relatively
    1.34
    Activations Density 1.356%

    No Known Activations