© 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. 34-GEMMASCOPE-RES-131K
    4. 1985
    Prev
    Next
    INDEX
    Explanations

    numbers and measurements

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

    The neuron is specialized to detect numeric tokens (multi-digit numbers) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     and
    -1.49
     first
    -1.36
     with
    -1.05
    himovic
    -1.05
     also
    -0.98
    <bos>
    -0.97
     largest
    -0.93
    '">
    -0.93
    ius
    -0.93
    iel
    -0.93
    POSITIVE LOGITS
    為に
    1.09
     ANOTHER
    1.07
    さあ
    1.04
     sés
    1.04
     emballage
    1.03
    になれば
    1.02
     gratuite
    0.98
     spéciales
    0.98
     éte
    0.98
     prohibido
    0.97
    Activations Density 0.058%

    No Known Activations