© 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. 38867
    Prev
    Next
    INDEX
    Explanations

    X of Y structure

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

    The neuron strongly activates on numeric tokens (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
     and
    -1.17
     dépenses
    -1.16
    仍然
    -1.15
     ‘’
    -1.14
     preval
    -1.14
    the
    -1.14
    about
    -1.13
     attirer
    -1.09
     colossal
    -1.09
    ode
    -1.08
    POSITIVE LOGITS
     that
    2.02
     which
    1.45
     atau
    1.41
     only
    1.40
     had
    1.38
     all
    1.37
    ತ್
    1.31
     not
    1.30
    alami
    1.28
     for
    1.25
    Activations Density 0.036%

    No Known Activations