© 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. 99182
    Prev
    Next
    INDEX
    Explanations

    foreign exchange certificate

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

    This neuron specifically detects mentions of the TV show “The Cosby Show” (especially the token “Cosby”).

    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
     Hiros
    -0.72
    疏
    -0.71
     testigos
    -0.69
    Stadt
    -0.68
     Elton
    -0.68
     Shorts
    -0.66
    chang
    -0.66
    abonnement
    -0.66
     lung
    -0.65
     Britney
    -0.65
    POSITIVE LOGITS
     Cosby
    1.19
     Pudding
    0.96
     pudding
    0.83
    вет
    0.81
    endant
    0.80
    TAS
    0.79
    ALERT
    0.71
     Cliff
    0.71
     Camille
    0.70
    CVS
    0.69
    Activations Density 0.018%

    No Known Activations