© 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. 34-GEMMASCOPE-RES-131K
    7. 49491
    Prev
    Next
    INDEX
    Explanations

    Martha + last name

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

    This neuron responds to occurrences of the name “Martha.”

    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
    )$
    -0.84
     роман
    -0.81
    })$
    -0.81
    Wave
    -0.79
    Condition
    -0.77
    //--
    -0.77
    КА
    -0.77
     separa
    -0.76
     軍
    -0.76
     ACADEM
    -0.75
    POSITIVE LOGITS
     Stewart
    0.96
    ślę
    0.88
     Vineyard
    0.86
    Stewart
    0.80
    에게
    0.79
    viš
    0.79
     pursuits
    0.77
    炜
    0.77
    ónio
    0.77
     esfuerzo
    0.77
    Activations Density 0.014%

    No Known Activations