© 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. 28113
    Prev
    Next
    INDEX
    Explanations

    start of quote or list item

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

    The neuron activates on numeric literals (sequences of digits, including numbers in code or configuration).

    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
    -1.06
     those
    -1.05
     relation
    -0.97
     紹介
    -0.88
    太过
    -0.85
     Româ
    -0.84
     sezon
    -0.84
     also
    -0.83
    ଓ
    -0.82
    セリフ
    -0.82
    POSITIVE LOGITS
     or
    1.32
     или
    1.04
     Yes
    1.01
    __':
    0.96
    dfrac
    0.95
    disha
    0.93
    Yes
    0.93
    前面的
    0.89
     dokład
    0.88
    𝐧
    0.88
    Activations Density 0.006%

    No Known Activations