© 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. 28557
    Prev
    Next
    INDEX
    Explanations

    anticoagulant

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

    This neuron identifies colons that introduce a list, particularly in informational or instructional content.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    This neuron detects colon characters (":") in the text, especially those introducing lists or section headings.

    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
     to
    -1.77
     when
    -1.70
     of
    -1.56
     where
    -1.55
     as
    -1.52
     probably
    -1.48
     there
    -1.45
     only
    -1.43
     for
    -1.41
     some
    -1.41
    POSITIVE LOGITS
     réjou
    1.50
     imprimer
    1.44
     rembour
    1.39
     araña
    1.39
     energii
    1.38
     refroid
    1.30
     réinitial
    1.27
    corrhi
    1.26
     offrir
    1.23
     první
    1.23
    Activations Density 0.016%

    No Known Activations