© 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. 65695
    Prev
    Next
    INDEX
    Explanations

    sequence or next step

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

    This neuron lights up on very common, high‐frequency “function” words and generic terms (e.g. articles, prepositions, auxiliary verbs, simple quantifiers) rather than specific content 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
     both
    -1.12
     which
    -0.94
     would
    -0.94
     could
    -0.89
     EVERY
    -0.87
     because
    -0.84
     reasons
    -0.83
    Enclosure
    -0.83
     longstanding
    -0.82
    ଚ
    -0.81
    POSITIVE LOGITS
     násled
    1.07
     continuación
    1.00
     then
    0.97
    Após
    0.96
     vervolgens
    0.93
    和你
    0.90
     Após
    0.89
    必须
    0.89
     Après
    0.88
    PHASE
    0.88
    Activations Density 0.079%

    No Known Activations