© 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. 58345
    Prev
    Next
    INDEX
    Explanations

    academic conferences and publications

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

    The main thing this neuron does is detect numeric tokens (such as years, page numbers, conference identifiers, and other digit sequences).

    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
     when
    -1.04
     dragged
    -0.85
    When
    -0.85
     fairly
    -0.84
     kids
    -0.82
     sometimes
    -0.81
     by
    -0.80
     consultants
    -0.79
    Still
    -0.76
     primarily
    -0.75
    POSITIVE LOGITS
     IEEE
    1.18
     ACM
    1.12
    ACM
    1.06
    IEEE
    1.01
     SIG
    0.96
     конферен
    0.89
     Workshop
    0.89
     WWW
    0.86
     Conference
    0.84
     Artificial
    0.83
    Activations Density 0.012%

    No Known Activations