© 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. 79188
    Prev
    Next
    INDEX
    Explanations

    eligibility and participation

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

    The neuron is keyed to numerical tokens—years, program codes, dollar amounts, and other multi-digit numbers.

    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
     когато
    -1.08
    ∛
    -1.07
     when
    -1.06
     учета
    -1.01
    难
    -0.91
     ALWAYS
    -0.90
    ADELPHIA
    -0.90
    inflater
    -0.88
     that
    -0.88
    FileReader
    -0.88
    POSITIVE LOGITS
     eligible
    2.19
     interested
    1.98
     successful
    1.94
     applicants
    1.81
     participants
    1.69
     eligibility
    1.64
     criteria
    1.59
    successful
    1.52
     anyone
    1.51
     requirements
    1.38
    Activations Density 0.064%

    No Known Activations