© 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. 10-GEMMASCOPE-RES-131K
    7. 45307
    Prev
    Next
    INDEX
    Explanations

    user, group, roles, settings

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

    This neuron fires on code‐style identifiers and type names (e.g. class, controller, device, user, group, settings, principal) rather than ordinary words.

    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
    訁
    -2.09
     två
    -2.09
    饪
    -2.08
    絎
    -1.99
    盉
    -1.98
     ١
    -1.96
    缯
    -1.91
     tunik
    -1.85
     dieß
    -1.84
    ⃞
    -1.84
    POSITIVE LOGITS
    :
    2.38
    <i>
    2.33
    塤
    1.91
    的区别
    1.89
    </th>
    1.80
    ꦤ
    1.78
     misschien
    1.77
    та
    1.75
     vollkommen
    1.75
    ou
    1.69
    Activations Density 0.021%

    No Known Activations