© 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. 44615
    Prev
    Next
    INDEX
    Explanations

    a block, counter, method, file

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

    The neuron responds to numeric tokens, i.e. numbers and numerical values 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_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
     vagas
    -1.44
     atitude
    -1.36
     saia
    -1.30
     beira
    -1.29
     imedi
    -1.29
     Paesi
    -1.26
    🕒
    -1.23
     tormenta
    -1.22
     maire
    -1.20
     normes
    -1.20
    POSITIVE LOGITS
     когда
    1.52
     now
    1.49
     also
    1.49
     zwi
    1.41
    ).
    1.40
     teléfonos
    1.38
     artísticas
    1.38
     camiones
    1.35
    nowu
    1.33
    anches
    1.31
    Activations Density 0.109%

    No Known Activations