© 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. 34-GEMMASCOPE-RES-131K
    7. 106755
    Prev
    Next
    INDEX
    Explanations

    said , :

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

    The neuron strongly activates on numeric tokens and related units (e.g. digits, “lakh,” “crore”) denoting large quantities or financial figures.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    anku
    -0.90
    yně
    -0.87
    seurs
    -0.85
     yesterday
    -0.82
    恙
    -0.80
    ophiles
    -0.80
    iettes
    -0.79
    一抹
    -0.78
    ysty
    -0.77
    miary
    -0.76
    POSITIVE LOGITS
     PTI
    1.20
     Erkrankung
    0.86
    ่าน
    0.79
    wasn
    0.77
    RequestId
    0.76
     Krankheit
    0.74
     seleccione
    0.73
    GREES
    0.72
     Coo
    0.71
     不是
    0.71
    Activations Density 0.004%

    No Known Activations