© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 75477
    Prev
    Next
    INDEX
    Explanations

    known as or called

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

    The neuron detects phrasing that introduces or signals an alternative name, alias, or common/local term (e.g. “known locally as,” “called,” “commonly referred to as”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     allegedly
    -1.00
     comparable
    -0.92
    並且
    -0.90
    屬於
    -0.89
     potentially
    -0.85
     Umfeld
    -0.85
    無し
    -0.84
     promising
    -0.84
     supposedly
    -0.84
    属于
    -0.82
    POSITIVE LOGITS
     collo
    1.63
    collo
    1.38
     colloquial
    1.37
     daglig
    1.28
     shorthand
    1.25
     in
    1.16
     Collo
    1.13
     affectionate
    1.13
     locals
    1.13
     vernacular
    1.08
    Activations Density 0.090%

    No Known Activations