© 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. 22-GEMMASCOPE-RES-131K
    7. 27299
    Prev
    Next
    INDEX
    Explanations

    phone number or name

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

    The neuron strongly activates on the possessive “our” (and closely following words like “services,” “quality,” etc.) in self-promotional business or service descriptions.

    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
     フィギュア
    -1.04
    𝒙
    -1.00
    迥
    -0.99
     telur
    -0.96
     цвят
    -0.95
     continuación
    -0.94
    philosophy
    -0.93
     väg
    -0.91
     jagung
    -0.91
     wirklich
    -0.90
    POSITIVE LOGITS
     noastre
    0.96
     子ども
    0.95
     is
    0.93
    当店
    0.92
    러
    0.91
    ällig
    0.91
    蟎
    0.90
    theo
    0.89
    có
    0.89
    في
    0.88
    Activations Density 0.001%

    No Known Activations