© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 35370
    Prev
    Next
    INDEX
    Explanations

    in the

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

    The neuron activates on numeric tokens (especially three‐digit 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
     which
    -1.48
     having
    -1.31
     or
    -1.18
    昃
    -1.16
    十二月
    -1.15
     respectively
    -1.14
     líqu
    -1.14
    toDouble
    -1.14
     including
    -1.10
     should
    -1.09
    POSITIVE LOGITS
     Respuesta
    1.18
    但却
    1.17
    出了一
    1.17
     
    1.16
     angefangen
    1.10
    めちゃくちゃ
    1.06
    ⁽
    1.06
     geplant
    1.06
    pixabay
    1.06
     alcune
    1.05
    Activations Density 0.065%

    No Known Activations