© 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. 93027
    Prev
    Next
    INDEX
    Explanations

    according to studies

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

    The neuron detects words and phrases characteristic of genealogical surname‐origin or family‐history entries.

    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
     from
    -1.04
     in
    -0.93
     took
    -0.92
     at
    -0.90
     on
    -0.90
     or
    -0.90
     خوردن
    -0.88
    気味
    -0.87
     bereaved
    -0.86
     before
    -0.86
    POSITIVE LOGITS
     olabilir
    1.07
    į
    1.05
    ugges
    1.04
    pecially
    1.02
    ۪
    1.01
    €¦
    1.00
    uits
    0.99
    ┬
    0.99
     ſon
    0.98
    mogen
    0.97
    Activations Density 0.004%

    No Known Activations