© 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. 63896
    Prev
    Next
    INDEX
    Explanations

    event registration

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

    The neuron is detecting numeric tokens (digits and number–unit combinations) such as dates, times, distances, and other numeric event details.

    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
     Formel
    -0.91
    苷
    -0.75
    Invitation
    -0.73
    skab
    -0.73
    inys
    -0.72
    声が
    -0.72
    اخته
    -0.71
     Seat
    -0.71
    ));
    -0.71
    ây
    -0.71
    POSITIVE LOGITS
     registration
    2.38
     Registration
    1.93
    registration
    1.84
     registrations
    1.82
    Registration
    1.81
     awards
    1.63
     registered
    1.57
     register
    1.55
     registering
    1.55
     REGISTRATION
    1.49
    Activations Density 0.018%

    No Known Activations