© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 72669
    Prev
    Next
    INDEX
    Explanations

    chemical characterizing goals

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

    numerical coordinates in technical or programming contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron activates on numeric literals—especially numbers with decimal points—used to specify coordinates, dimensions, or other measurements in code or markup.

    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
     that
    -1.53
     this
    -1.49
     the
    -1.41
     as
    -1.31
     a
    -1.24
     without
    -1.22
     our
    -1.21
     those
    -1.20
     how
    -1.18
     for
    -1.17
    POSITIVE LOGITS
     sombr
    1.34
    쐈
    1.25
     joyeux
    1.25
     délicieux
    1.23
    varande
    1.20
     obed
    1.19
    issez
    1.18
    tehen
    1.17
     varier
    1.16
     voulu
    1.15
    Activations Density 0.008%

    No Known Activations