© 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. 10-GEMMASCOPE-RES-131K
    7. 105345
    Prev
    Next
    INDEX
    Explanations

    menstrual cycle abnormalities

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

    acronyms and technical or scientific compound terms.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    This neuron activates on numeric tokens (i.e. standalone numbers, including integers and decimals).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    ’
    -3.55
    {
    -3.11
    &
    -3.06
    ”
    -2.80
    ve
    -2.44
    $,
    -2.39
    '
    -2.28
     内衣
    -2.22
    ꯹
    -2.20
    蘧
    -2.17
    POSITIVE LOGITS
    檍
    2.48
     résulte
    2.39
    蜴
    2.33
     conocidas
    2.30
     apparaît
    2.27
    自体は
    2.25
     affirme
    2.25
     penchant
    2.22
    ⃤
    2.17
     faisait
    2.16
    Activations Density 0.066%

    No Known Activations