© 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. 22-GEMMASCOPE-RES-131K
    7. 39865
    Prev
    Next
    INDEX
    Explanations

    one, only, exception

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

    The neuron activates on numeric expressions and counts— spotting numbers (dates, quantities, chapter counts, etc.) and their immediate context.

    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
     berbagai
    -1.18
    Again
    -1.17
     again
    -1.16
    again
    -1.11
     baden
    -1.10
    今度は
    -1.08
     இந்த
    -1.06
     Again
    -1.05
    ณฑ
    -1.02
     allerlei
    -1.02
    POSITIVE LOGITS
     its
    1.16
     because
    1.16
     only
    1.12
     exception
    1.01
     there
    0.99
    特殊
    0.99
     केवल
    0.97
     special
    0.96
     медици
    0.94
    parseDouble
    0.94
    Activations Density 0.071%

    No Known Activations