© 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. 83393
    Prev
    Next
    INDEX
    Explanations

    is or isn't

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

    The neuron fires on words that name or point to people or groups—pronouns, proper names, and nouns referring to social entities.

    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
    assertRaises
    -0.90
     were
    -0.87
    toThrow
    -0.86
     will
    -0.84
    (!$
    -0.84
     никак
    -0.82
    zyny
    -0.80
     Don
    -0.80
     لا
    -0.79
     никаких
    -0.78
    POSITIVE LOGITS
     isn
    7.19
     aren
    5.66
     Isn
    4.13
     isnt
    4.00
     wasn
    4.00
    Isn
    3.88
    不是
    3.64
     نیست
    3.56
    isn
    3.52
     weren
    3.20
    Activations Density 0.286%

    No Known Activations