© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 97958
    Prev
    Next
    INDEX
    Explanations

    code structure identifiers

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

    This neuron activates on standalone numeric tokens (i.e. 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_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
     instantly
    -0.85
     Depression
    -0.81
     episódio
    -0.80
     Talvez
    -0.76
     then
    -0.76
     quickly
    -0.76
     Herramientas
    -0.75
     commonly
    -0.75
    carolina
    -0.75
    هور
    -0.74
    POSITIVE LOGITS
     past
    1.21
    PAST
    1.17
    past
    1.13
     PAST
    1.08
    Past
    0.97
     gebildet
    0.87
     clerical
    0.87
     Past
    0.86
     pasado
    0.83
     Suez
    0.83
    Activations Density 0.000%

    No Known Activations