© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 71217
    Prev
    Next
    INDEX
    Explanations

    seconds i

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

    The neuron strongly activates on standalone numeric tokens (i.e. isolated numbers or numeric ranges).

    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
     demselben
    -0.96
     will
    -0.93
     полови
    -0.89
    意義
    -0.89
    注意事項
    -0.88
     chỉ
    -0.88
    gridColumn
    -0.84
     over
    -0.82
     anschließend
    -0.82
     rồi
    -0.81
    POSITIVE LOGITS
     дочь
    0.95
     braços
    0.94
    なもの
    0.93
     både
    0.93
     arrêter
    0.92
     éviter
    0.91
     occafion
    0.86
    ˮ
    0.85
     vocales
    0.84
     fufficient
    0.84
    Activations Density 0.068%

    No Known Activations