© 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. 10-GEMMASCOPE-RES-131K
    7. 74292
    Prev
    Next
    INDEX
    Explanations

    Foreign words and names

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

    This neuron detects capitalized proper nouns—especially personal and organizational names.

    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
     if
    -1.44
     some
    -1.30
    }
    -1.27
    許多
    -1.25
     некоторые
    -1.20
     bazı
    -1.20
    Some
    -1.19
    を紹介します
    -1.18
     некоторых
    -1.16
    Surprisingly
    -1.16
    POSITIVE LOGITS
     zwi
    1.20
     другого
    1.19
    лкой
    1.16
     zawsze
    1.06
    ();
    1.05
     fahrrad
    1.03
     holz
    1.02
    呃
    1.02
     ogrodow
    1.02
     eventually
    1.02
    Activations Density 0.166%

    No Known Activations