© 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. 26929
    Prev
    Next
    INDEX
    Explanations

    businesses and services

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

    The neuron fires most strongly on technical product or architecture version identifiers and model numbers (e.g. “v 8,” “ARM v8,” “Cortex™-227”).

    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
    -2.00
     had
    -1.95
     other
    -1.91
     those
    -1.81
     did
    -1.70
     this
    -1.65
     now
    -1.65
     still
    -1.60
     their
    -1.58
     usually
    -1.58
    POSITIVE LOGITS
     faciliter
    1.59
     шокола
    1.52
    Furthermore
    1.52
     accompagner
    1.48
     favoriser
    1.42
     réinitial
    1.41
    irical
    1.40
     قوة
    1.40
     egenskaper
    1.38
     スリーブ
    1.38
    Activations Density 0.112%

    No Known Activations