© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 13669
    Prev
    Next
    INDEX
    Explanations

    HTML closing tags and content

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

    The neuron detects tokens that are purely numeric or contain numeric digits (i.e. number literals inside HTML or code).

    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
     that
    -1.30
     those
    -1.21
     this
    -1.21
     of
    -1.19
     when
    -1.16
     how
    -1.10
     what
    -1.09
     these
    -1.06
     where
    -1.02
    When
    -1.02
    POSITIVE LOGITS
     remplissage
    1.15
     disgruntled
    1.12
     bénéfice
    1.10
     coffret
    1.10
     trots
    1.09
    σιν
    1.09
    begins
    1.08
     inept
    1.08
     trajets
    1.07
     continúan
    1.07
    Activations Density 0.001%

    No Known Activations