© 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. 84370
    Prev
    Next
    INDEX
    Explanations

    language codes, nation names

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

    The neuron fires on uppercase multi-letter acronyms (like AMP, HIF-1α, CAP) represented as tokens in all caps.

    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
     which
    -1.41
    There
    -1.21
     as
    -1.19
     getting
    -1.19
    What
    -1.16
     creating
    -1.12
     When
    -1.11
     one
    -1.09
     from
    -1.08
     Getting
    -1.08
    POSITIVE LOGITS
     onCancelled
    1.16
     molti
    1.08
     parlement
    1.05
    Frans
    1.04
     SECUR
    0.99
     plusieurs
    0.98
     spate
    0.98
     суток
    0.98
     frans
    0.97
     molte
    0.96
    Activations Density 0.001%

    No Known Activations