© 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. 73672
    Prev
    Next
    INDEX
    Explanations

    behind something

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

    The neuron activates on numeric tokens (including integers and decimals), i.e. it’s detecting numbers.

    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
    )
    -2.13
     up
    -1.88
     in
    -1.80
     out
    -1.71
    '
    -1.67
     will
    -1.58
     This
    -1.41
    afterEach
    -1.40
    *
    -1.40
     资料
    -1.36
    POSITIVE LOGITS
    behind
    1.77
     detrás
    1.68
    arschu
    1.63
     derrière
    1.57
     Behind
    1.56
     ними
    1.52
    Behind
    1.51
     BEHIND
    1.46
     makin
    1.45
     theſe
    1.41
    Activations Density 0.018%

    No Known Activations