© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 73336
    Prev
    Next
    INDEX
    Explanations

    20xx years

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

    The neuron strongly activates on the single character “2,” i.e. occurrences of the digit two.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    掂
    -1.84
    𝝈
    -1.77
    ']:
    -1.70
     cilindros
    -1.70
    ်း
    -1.69
     actriz
    -1.68
    (")
    -1.67
    ']]
    -1.66
     actos
    -1.66
     vám
    -1.64
    POSITIVE LOGITS
    Interestingly
    1.75
    When
    1.73
    Ironically
    1.71
    /
    1.71
     Siehe
    1.70
     Luckily
    1.70
    0
    1.70
     Interestingly
    1.70
     This
    1.69
     最後
    1.66
    Activations Density 0.143%

    No Known Activations