© 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. 85999
    Prev
    Next
    INDEX
    Explanations

    multilingual or diverse tokens

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

    The neuron fires on action‐oriented verbs (and their associated structural words) that define or describe steps, entities, or operations in technical/procedural contexts.

    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
     their
    -2.00
     thier
    -1.43
     some
    -1.39
    鹘
    -1.36
     who
    -1.36
    <th>
    -1.33
    ஊ
    -1.32
    </strong>
    -1.30
    过敏
    -1.28
     these
    -1.27
    POSITIVE LOGITS
    ↵↵
    1.64
     =
    1.37
     will
    1.16
    ينو
    1.16
    quois
    1.14
    راهن
    1.14
     människor
    1.13
     répondit
    1.13
    pagnole
    1.13
    pezi
    1.13
    Activations Density 0.206%

    No Known Activations