© 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. 84536
    Prev
    Next
    INDEX
    Explanations

    individual items or groups

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

    The neuron detects numerical values, especially multi-digit numbers or numbers with decimal points.

    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
    possibly
    -2.16
    probably
    -2.06
    perhaps
    -2.00
     usando
    -2.00
     specif
    -1.99
     vijf
    -1.96
     joyful
    -1.95
     THROUGH
    -1.93
     unbelievably
    -1.86
     dando
    -1.84
    POSITIVE LOGITS
     from
    2.44
     EVERY
    2.36
     for
    2.20
     overtly
    2.20
     in
    2.20
     with
    2.16
     Each
    2.13
     that
    2.09
     Every
    2.09
     makes
    2.06
    Activations Density 0.050%

    No Known Activations