© 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. 79797
    Prev
    Next
    INDEX
    Explanations

    sequences starting with common words

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

    The neuron fires on numeric tokens in code (integer literals and numeric parts of types or constants).

    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
     it
    -1.20
     with
    -1.18
     this
    -1.11
     celebrid
    -1.06
     in
    -1.06
     założ
    -1.00
     when
    -0.99
     if
    -0.96
     fees
    -0.96
     doros
    -0.96
    POSITIVE LOGITS
    ʞ
    1.26
    嵎
    1.20
     vermel
    1.13
    ὺς
    1.13
     médicaments
    1.12
    ῖς
    1.10
     maniere
    1.09
     constater
    1.09
    ➀
    1.08
     gespeichert
    1.07
    Activations Density 0.002%

    No Known Activations