© 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. 10-GEMMASCOPE-RES-131K
    7. 40306
    Prev
    Next
    INDEX
    Explanations

    establishing a fact or outcome

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

    The neuron fires on multi‐syllabic, affixed English verbs—i.e. verbs built with a Latin‐style prefix plus root.

    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
     history
    -1.52
     rationale
    -1.39
    ation
    -1.30
    ."
    -1.23
     gelb
    -1.22
    druk
    -1.21
    veling
    -1.19
     heiß
    -1.17
     étoient
    -1.17
     his
    -1.16
    POSITIVE LOGITS
    <tr>
    1.66
     it
    1.55
     şun
    1.34
    щие
    1.34
     Paralymp
    1.32
     marzo
    1.30
     versões
    1.30
     fortfarande
    1.29
    🢒
    1.28
    ​​​​
    1.27
    Activations Density 0.242%

    No Known Activations