© 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. 22-GEMMASCOPE-RES-131K
    7. 33957
    Prev
    Next
    INDEX
    Explanations

    first or earliest instance

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

    This neuron detects claims of being first or early/pioneering—words signaling an organization’s ordinal or founding status (e.g., “first,” “pioneers,” “founding”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     検
    -1.25
     beantragt
    -1.07
     predominantly
    -1.02
    replace
    -1.00
    inherits
    -1.00
    iress
    -0.99
     verwal
    -0.98
     sedang
    -0.98
    正在
    -0.98
     последний
    -0.97
    POSITIVE LOGITS
     earliest
    1.76
     early
    1.69
     started
    1.58
    แรก
    1.39
     since
    1.39
     when
    1.37
    最早
    1.34
     before
    1.28
     pioneered
    1.22
     originally
    1.20
    Activations Density 0.064%

    No Known Activations