© 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. 71319
    Prev
    Next
    INDEX
    Explanations

    Press Release

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

    The main thing this neuron does is identify numeric tokens (i.e. standalone 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
     these
    -1.00
     this
    -0.98
    These
    -0.98
     powiedzieć
    -0.96
    What
    -0.95
    Does
    -0.94
    This
    -0.92
     through
    -0.92
     garcía
    -0.91
     what
    -0.90
    POSITIVE LOGITS
     capaces
    1.05
     varones
    0.98
     deta
    0.97
    ＊＊＊
    0.96
    锹
    0.93
     llenos
    0.92
     whirl
    0.90
    COUNTS
    0.90
     incarcer
    0.90
    集中
    0.90
    Activations Density 0.000%

    No Known Activations