© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 95834
    Prev
    Next
    INDEX
    Explanations

    mathematical and code expressions

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

    This neuron responds to numeric tokens, i.e. it detects numbers (digits or multi‐digit numerical expressions) 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
     stratég
    -1.39
    yyj
    -1.38
     tropicales
    -1.37
    hogy
    -1.36
     besonder
    -1.31
     bolsos
    -1.31
     asiática
    -1.30
     nô
    -1.30
     vernis
    -1.28
     trône
    -1.28
    POSITIVE LOGITS
    ;
    1.34
    fillment
    1.27
     one
    1.19
    B
    1.18
     these
    1.13
     obligé
    1.09
    _
    1.09
     that
    1.09
    ];
    1.08
    b
    1.08
    Activations Density 0.002%

    No Known Activations