© 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. 34-GEMMASCOPE-RES-131K
    7. 63798
    Prev
    Next
    INDEX
    Explanations

    closing punctuation or tags

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

    The neuron is activated almost exclusively by standalone period tokens (full stops).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     on
    -1.59
     can
    -1.53
     by
    -1.37
     large
    -1.25
     all
    -1.25
     larger
    -1.23
     in
    -1.22
     one
    -1.14
     may
    -1.13
     not
    -1.11
    POSITIVE LOGITS
    躥
    1.05
    räumen
    1.05
     Nuo
    1.05
     इस्त
    1.05
     trám
    1.03
     coerci
    1.03
     insanely
    1.03
     zugel
    1.02
     dreary
    1.01
     Auteur
    1.01
    Activations Density 0.001%

    No Known Activations