© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 13932
    Prev
    Next
    INDEX
    Explanations

    mathematical or code contexts

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

    The neuron is strongly activated by occurrences of the mathematical‐relation token “in” (and related set‐membership words like “subset”), i.e. it flags membership expressions.

    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
    それを
    -2.13
    1
    -2.02
    u
    -1.99
    7
    -1.97
    8
    -1.96
    to
    -1.89
    );
    -1.84
    や
    -1.84
    as
    -1.80
     что
    -1.80
    POSITIVE LOGITS
    んですね
    1.91
    Begriffsklä
    1.78
    んですよね
    1.77
     asomb
    1.75
    TryDecode
    1.71
    咘
    1.67
     soñ
    1.63
    んですが
    1.63
     algun
    1.61
     debía
    1.59
    Activations Density 0.004%

    No Known Activations