© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 71553
    Prev
    Next
    INDEX
    Explanations

    the followed by controllable entities

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

    The neuron highlights words that denote control, management, or responsibility over a process (e.g. “responsible,” “manages,” “controlling,” “governing”).

    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
     Ahnung
    -1.80
    <h2>
    -1.61
     Publicar
    -1.48
     lends
    -1.47
     nearby
    -1.43
    lardır
    -1.41
     
    -1.41
     Crear
    -1.41
    ultu
    -1.41
    5
    -1.38
    POSITIVE LOGITS
     cabine
    1.96
     applau
    1.89
     fraude
    1.80
    queous
    1.78
    </em>
    1.72
    鉝
    1.71
    konos
    1.68
     industrie
    1.67
     geh
    1.66
     malen
    1.65
    Activations Density 0.054%

    No Known Activations