© 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. 22-GEMMASCOPE-RES-131K
    7. 26470
    Prev
    Next
    INDEX
    Explanations

    citations and numbers

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

    The neuron activates on numeric tokens (e.g. numbers, percentages, reference indices).

    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
     Undoubtedly
    -1.05
    noons
    -1.05
     transparence
    -1.04
     adil
    -1.02
     Evidently
    -1.02
     Obviously
    -1.02
     bair
    -1.02
    чности
    -1.01
     comesti
    -1.01
     régiment
    -1.00
    POSITIVE LOGITS
     cinq
    1.15
    three
    1.14
     !!!!!
    1.06
     !!!!
    1.03
     Donnerstag
    0.99
     trois
    0.99
    want
    0.98
    six
    0.98
     drei
    0.98
    两个
    0.97
    Activations Density 0.045%

    No Known Activations