© 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. 10-GEMMASCOPE-RES-131K
    7. 101105
    Prev
    Next
    INDEX
    Explanations

    citation markers and punctuation

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

    This neuron responds to standalone numeric values (especially decimals) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     with
    -2.52
     from
    -2.44
     to
    -2.39
     in
    -2.27
     on
    -2.25
     so
    -2.08
     for
    -2.06
     as
    -2.05
     also
    -2.02
     their
    -1.98
    POSITIVE LOGITS
     refroid
    2.48
     autonomie
    2.11
     éta
    2.09
    我們
    2.08
    慙
    2.06
     apporter
    1.96
     navideños
    1.95
    Daftar
    1.95
     sonre
    1.95
    ين
    1.91
    Activations Density 0.008%

    No Known Activations