© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 72808
    Prev
    Next
    INDEX
    Explanations

    scientific fields and units

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

    scientific research settings with laboratories, experiments, or study locations.

    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
     so
    -1.30
     isn
    -1.27
     you
    -1.21
     if
    -1.19
     because
    -1.09
     what
    -1.09
     then
    -1.09
     too
    -1.07
     your
    -1.05
    archical
    -1.03
    POSITIVE LOGITS
    اقتصاد
    1.13
    Cevap
    1.10
    whose
    1.09
     froid
    1.09
     awakeFromNib
    1.08
     държа
    1.08
     péché
    1.08
     conva
    1.07
     matar
    1.05
     volontaire
    1.05
    Activations Density 0.981%

    No Known Activations