© 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. 65113
    Prev
    Next
    INDEX
    Explanations

    number sequences following parentheses

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

    The neuron detects numeric tokens (digits or numbers) in the text.

    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
    /).
    -1.18
     sehr
    -1.12
     (
    -1.12
    größ
    -1.11
    <bos>
    -1.11
     is
    -1.09
     under
    -1.08
     informée
    -1.07
     ofta
    -1.06
     fotográfico
    -1.06
    POSITIVE LOGITS
     schreef
    1.20
    為に
    1.16
    至少
    1.13
     stiefel
    1.09
     almeno
    1.09
     vencedor
    1.07
     qualunque
    1.07
    ولايات
    1.05
     garcía
    1.05
     citroen
    1.05
    Activations Density 0.046%

    No Known Activations