© 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. 34-GEMMASCOPE-RES-131K
    4. 33498
    Prev
    Next
    INDEX
    Explanations

    mathematical and scientific notation

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

    The neuron is detecting long sequences of digits (multi‐digit numbers).

    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
     (
    -1.02
     aforementioned
    -1.02
     –
    -1.01
     where
    -1.00
     because
    -0.96
     when
    -0.92
     triliun
    -0.92
     didn
    -0.91
     or
    -0.90
     cerdas
    -0.88
    POSITIVE LOGITS
    ?,
    1.07
    #,
    1.06
    ²,
    1.05
     (),
    1.04
     {},
    1.02
     ?,
    1.00
    **,
    1.00
    ],
    0.96
    ;,
    0.96
     [],
    0.96
    Activations Density 0.004%

    No Known Activations