© 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. 118215
    Prev
    Next
    INDEX
    Explanations

    Realtor, Engineers, Standard

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

    The neuron is triggered by multi-token, capitalized proper names and formal entity titles (e.g. long organization or program names in legal/boilerplate text).

    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
     cross
    -0.74
    gal
    -0.73
    cross
    -0.71
     left
    -0.69
     editor
    -0.69
     por
    -0.69
     Ald
    -0.69
    車は
    -0.68
    转换成
    -0.68
    gle
    -0.67
    POSITIVE LOGITS
     RP
    1.05
     NAR
    0.98
    NAR
    0.98
     Realtors
    0.92
    RP
    0.91
     Realtor
    0.88
    ®.
    0.86
    ®,
    0.79
     REAL
    0.75
     GAR
    0.75
    Activations Density 0.032%

    No Known Activations