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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 35041
    Prev
    Next
    INDEX
    Explanations

    medical, scientific, or legal abstracts

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

    numbers in a data row or table format.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    This neuron is effectively inactive and does not respond to any specific text patterns.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     that
    -2.33
     if
    -2.13
     in
    -2.09
     with
    -2.02
     because
    -1.95
     for
    -1.90
     as
    -1.88
    hasilkan
    -1.86
     after
    -1.85
    although
    -1.85
    POSITIVE LOGITS
     …
    2.53
     …..
    2.17
     &
    2.08
    en
    2.05
     delightfully
    2.00
    ut
    2.00
    ar
    1.98
    /
    1.95
     insanely
    1.94
     wacky
    1.93
    Activations Density 0.000%

    No Known Activations