© 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. 22-GEMMASCOPE-RES-131K
    7. 15708
    Prev
    Next
    INDEX
    Explanations

    HTML lists and tables

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

    The neuron is keyed to numeric characters (i.e. literal numbers) 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_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
     from
    -1.31
     that
    -1.23
     between
    -0.94
     by
    -0.92
     in
    -0.89
     having
    -0.89
     if
    -0.88
     with
    -0.88
     using
    -0.88
     filepath
    -0.88
    POSITIVE LOGITS
     almak
    0.93
     vēl
    0.93
    Filler
    0.90
     horaires
    0.90
     banques
    0.88
    ............
    0.87
    ..............
    0.84
     farklı
    0.83
    INGO
    0.83
     énorm
    0.83
    Activations Density 0.010%

    No Known Activations