© 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. 66811
    Prev
    Next
    INDEX
    Explanations

    versus, against, and

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

    The neuron fires on phrases that express a quantitative relationship between variables (e.g. “versus,” “against,” “function of,” “dependence on,” slashes indicating units).

    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
    などが
    -1.21
     ralenti
    -1.19
    ᠌
    -1.18
    翃
    -1.17
     marchandises
    -1.16
    
    -1.16
     APPELLANT
    -1.14
    ちなみに
    -1.14
     interesses
    -1.14
     chemins
    -1.12
    POSITIVE LOGITS
     time
    1.97
     increasing
    1.41
     February
    1.30
     at
    1.30
     October
    1.23
     each
    1.23
     in
    1.23
     September
    1.19
     hours
    1.17
     April
    1.17
    Activations Density 0.034%

    No Known Activations