© 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. 82642
    Prev
    Next
    INDEX
    Explanations

    alleges claims and accusations

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

    This neuron detects named entities—proper names of people, organizations, and other capitalized terms.

    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
    rdag
    -1.00
     aclar
    -0.89
     eigentlich
    -0.87
     explanation
    -0.87
    Herkunft
    -0.86
     joked
    -0.83
     Explanation
    -0.82
     Erklärung
    -0.81
    гти
    -0.81
    Katso
    -0.79
    POSITIVE LOGITS
     alleges
    3.44
     claim
    3.44
     claims
    3.39
     alleging
    3.09
     allege
    3.08
     claimed
    2.98
     allegation
    2.83
     allegations
    2.83
     claiming
    2.73
     alleged
    2.59
    Activations Density 0.057%

    No Known Activations