© 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. 14828
    Prev
    Next
    INDEX
    Explanations

    "A" prefixes

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

    The neuron responds specifically to standalone numeric tokens (sequences of digits) 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_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
     Since
    -2.48
     every
    -2.45
     When
    -2.39
     there
    -2.39
     each
    -2.38
     After
    -2.38
     From
    -2.36
     Although
    -2.31
     During
    -2.23
     both
    -2.16
    POSITIVE LOGITS
    1
    2.58
    2.34
    0
    2.20
    2
    2.17
    ஂ
    2.08
     perioden
    2.03
    4
    1.99
     \
    1.97
     leven
    1.95
    Ⲉ
    1.92
    Activations Density 0.058%

    No Known Activations