© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 117743
    Prev
    Next
    INDEX
    Explanations

    party and party-related events

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

    This neuron responds when the text mentions “a house party” (i.e. the article “a” immediately followed by “house” and “party”).

    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
    getNombre
    -0.74
    jnych
    -0.74
     мат
    -0.74
    örü
    -0.73
     tiet
    -0.72
     tecniche
    -0.71
    Plen
    -0.70
     האם
    -0.70
    oló
    -0.69
    ják
    -0.69
    POSITIVE LOGITS
     party
    5.19
     parties
    4.41
    party
    3.95
    Party
    3.52
     Party
    3.45
    parties
    3.33
     PARTY
    3.27
     Parties
    3.22
    Parties
    3.17
    PARTY
    2.94
    Activations Density 0.069%

    No Known Activations