© 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. 7643
    Prev
    Next
    INDEX
    Explanations

    preventing corrosion or improving aspects

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

    The neuron activates on numeric tokens and numerical expressions (e.g. digits, decimals, quantities).

    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
     -
    -1.27
    entown
    -1.16
    所说的
    -1.12
     Ă
    -1.06
    这样做
    -1.04
    所说
    -1.03
     duong
    -1.02
     consegui
    -1.02
     and
    -1.01
     --
    -1.00
    POSITIVE LOGITS
     dejar
    1.34
     evangé
    1.27
     pueda
    1.24
     últimas
    1.20
    şe
    1.16
    glEnd
    1.16
    DÉ
    1.15
     actividades
    1.15
     kembali
    1.13
     memberikan
    1.11
    Activations Density 0.592%

    No Known Activations