© 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. 22-GEMMASCOPE-RES-131K
    7. 33225
    Prev
    Next
    INDEX
    Explanations

    Q: questions and replies, set statements

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

    The neuron strongly responds to any token containing digits—e.g. numeric literals or identifiers with 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_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
     their
    -1.23
    ALAND
    -1.16
     poetas
    -1.09
     valamint
    -1.05
     Medizin
    -1.03
    ciri
    -1.03
     the
    -1.02
     ?$
    -1.00
    enteri
    -1.00
     skry
    -0.98
    POSITIVE LOGITS
    焢
    1.13
     écart
    1.11
    Hermoso
    1.08
    终极
    1.08
     peluche
    1.05
    Dishwasher
    1.04
    と思ったら
    1.02
    哪怕
    1.02
    不一样的
    1.02
    Zutaten
    1.01
    Activations Density 0.000%

    No Known Activations