© 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. 67041
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation

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

    The neuron fires on tokens that are numeric (i.e. digits or numbers).

    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
     without
    -1.40
     from
    -1.30
     that
    -1.22
     its
    -1.22
     will
    -1.22
     over
    -1.12
     as
    -1.12
     by
    -1.10
     first
    -1.10
     both
    -1.09
    POSITIVE LOGITS
     incluso
    1.17
     implor
    1.06
     maniere
    1.06
     atmosfera
    1.04
     farine
    1.04
     impromptu
    1.03
     infuri
    1.02
     dangereux
    1.00
     sedu
    0.98
     Canucks
    0.98
    Activations Density 0.010%

    No Known Activations