© 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. 22-GEMMASCOPE-RES-131K
    7. 15497
    Prev
    Next
    INDEX
    Explanations

    foreign countries and languages

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

    The neuron strongly activates on standalone section‐style headings or labels (e.g. “Overview,” “iframe,” “Message Interface”) rather than ordinary running text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     やすい
    -1.00
    板块
    -0.89
     والأ
    -0.85
     anledning
    -0.83
    Số
    -0.82
     Optimize
    -0.81
    чественной
    -0.80
    Func
    -0.80
    ğunu
    -0.79
    変な
    -0.79
    POSITIVE LOGITS
     depuis
    0.94
    อีก
    0.90
     роман
    0.87
     ownership
    0.86
     sejak
    0.84
     теперь
    0.82
    <0xA3>
    0.80
     endet
    0.79
    ندق
    0.79
     Herak
    0.79
    Activations Density 0.001%

    No Known Activations