© 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. 84259
    Prev
    Next
    INDEX
    Explanations

    language constructs and programming code

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

    The neuron primarily detects numeric tokens (i.e. any token containing digits or representing numbers).

    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
     kré
    -1.03
     arī
    -0.98
     tehd
    -0.96
     ideje
    -0.95
    Açık
    -0.95
    關
    -0.94
     obuv
    -0.93
     ilmo
    -0.93
    সং
    -0.93
     tästä
    -0.92
    POSITIVE LOGITS
    下来的
    1.07
    fourths
    1.02
    itária
    0.99
    过来了
    0.98
    过来的
    0.97
    回来了
    0.97
     «
    0.97
    …
    0.93
    betic
    0.91
    lu
    0.90
    Activations Density 0.062%

    No Known Activations