© 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. 66220
    Prev
    Next
    INDEX
    Explanations

    comparing rates, differences, or changes

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

    The neuron fires on numeric tokens, identifying numbers or quantitative 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_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
     abſ
    -1.07
    俱
    -1.06
    sise
    -1.05
     لإ
    -1.03
     entrer
    -1.02
     bascul
    -1.02
     procent
    -1.01
     eventi
    -1.00
    ugd
    -1.00
     diſ
    -0.99
    POSITIVE LOGITS
     there
    1.46
     or
    1.45
     differences
    1.30
     between
    1.25
     changes
    1.24
     within
    1.16
     indicated
    1.16
     verschillen
    1.16
     in
    1.13
     using
    1.12
    Activations Density 0.020%

    No Known Activations