© 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. 10-GEMMASCOPE-RES-131K
    7. 102951
    Prev
    Next
    INDEX
    Explanations

    Beta, B, b, 2

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

    The neuron consistently activates on tokens containing the digit “2,” i.e. numeric “2” in identifiers or words.

    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
     a
    -2.42
     in
    -2.13
     not
    -2.09
     as
    -2.06
     before
    -2.05
     it
    -2.02
     through
    -2.00
     by
    -1.93
     which
    -1.88
     during
    -1.82
    POSITIVE LOGITS
    泚
    1.61
    '
    1.53
     ........
    1.44
     accep
    1.42
     .......
    1.41
     mostrando
    1.41
    踯
    1.38
    再一次
    1.32
    sister
    1.31
     manches
    1.31
    Activations Density 0.151%

    No Known Activations