© 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. 12998
    Prev
    Next
    INDEX
    Explanations

    from the

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

    The neuron activates on numeric tokens (sequences of digits, including integers and decimals).

    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
    *
    -1.18
     “
    -1.18
     ‘
    -1.14
     
    -1.09
     +
    -1.05
    l
    -1.02
    d
    -1.01
    e
    -1.00
    '
    -0.99
    ’
    -0.98
    POSITIVE LOGITS
    dekat
    1.18
    אמ
    1.09
    jedno
    1.09
     pencarian
    1.09
     viviendas
    1.09
     eût
    1.08
     Kullan
    1.05
    Ketika
    1.05
     laporan
    1.04
     pamamagitan
    1.04
    Activations Density 0.125%

    No Known Activations