© 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. 22-GEMMASCOPE-RES-131K
    7. 40126
    Prev
    Next
    INDEX
    Explanations

    Boat Cards

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

    This neuron fires on uncommon, content‐bearing tokens—e.g. proper names, brands, musical-chord labels, and other rare words—rather than on common function words.

    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
     nestled
    -1.18
     in
    -1.16
     at
    -1.15
     because
    -1.09
    Nitrate
    -1.08
     with
    -1.05
     ostensibly
    -1.04
     unrelenting
    -1.02
     fué
    -1.00
     philosophie
    -1.00
    POSITIVE LOGITS
     crucial
    1.40
     myriad
    1.30
     acclaimed
    1.29
     gigantic
    1.27
     renowned
    1.24
     strikingly
    1.23
     quintessential
    1.22
     deliciously
    1.21
    each
    1.20
    IC
    1.19
    Activations Density 0.000%

    No Known Activations