© 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. 68663
    Prev
    Next
    INDEX
    Explanations

    questions and titles

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

    The neuron is primarily picking up numeric literals (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_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
     its
    -1.11
     Biografie
    -0.99
     your
    -0.94
    schung
    -0.94
    visão
    -0.94
     kés
    -0.93
    ρούν
    -0.92
    caucasian
    -0.90
    づけ
    -0.89
    ッタリ
    -0.89
    POSITIVE LOGITS
    in
    0.96
    er
    0.91
    BSD
    0.85
     Dopo
    0.85
    뭘
    0.84
    请选择
    0.83
     спросил
    0.82
    なども
    0.82
     except
    0.82
    le
    0.81
    Activations Density 0.000%

    No Known Activations