© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 47482
    Prev
    Next
    INDEX
    Explanations

    financial or legal terms with asterisks

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

    The neuron selectively activates on numeric tokens (numbers, percentages, and other digit sequences) 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_34/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
    )))))
    -0.91
    \_
    -0.91
    hs
    -0.90
    \">\
    -0.88
    ;->
    -0.85
    .
    -0.84
    = 
    -0.84
    〉
    -0.84
    ks
    -0.82
    -}
    -0.81
    POSITIVE LOGITS
    *
    3.63
    *,
    3.06
    *.
    2.84
    *)
    2.80
    *
    2.69
     *
    2.59
    )*
    2.52
    ※
    2.52
    *",
    2.50
    *:
    2.48
    Activations Density 0.181%

    No Known Activations