© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 28619
    Prev
    Next
    INDEX
    Explanations

    certain / specific

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

    The neuron activates on numeric tokens (literal numbers) in the 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
    糞
    -1.00
     prakti
    -0.94
    гляд
    -0.92
    Jangan
    -0.88
    Ғ
    -0.86
    τηση
    -0.86
    本の
    -0.86
     acos
    -0.85
    Harmony
    -0.85
    ascin
    -0.85
    POSITIVE LOGITS
     certain
    1.08
    某个
    1.03
    lysses
    0.93
     bestimmte
    0.93
    Certain
    0.93
    cO
    0.91
     cubiertos
    0.91
     duża
    0.90
    ところに
    0.89
     certaines
    0.89
    Activations Density 0.062%

    No Known Activations