© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 124646
    Prev
    Next
    INDEX
    Explanations

    scientific and abstract terms

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

    scientific terminology and methodology terms like "theory," "effect," "test," "analysis," and "syndrome."

    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
     their
    -2.67
     only
    -2.53
     it
    -2.31
     not
    -2.09
     also
    -1.91
     its
    -1.86
     with
    -1.80
     that
    -1.73
     this
    -1.71
     even
    -1.68
    POSITIVE LOGITS
     СЕ
    1.48
     PRESENT
    1.43
     redenen
    1.42
     maniere
    1.41
    rdquo
    1.40
     hilsen
    1.37
    knows
    1.36
     adulte
    1.36
    zä
    1.35
     muchacha
    1.35
    Activations Density 0.631%

    No Known Activations