© 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. 10-GEMMASCOPE-RES-131K
    7. 100298
    Prev
    Next
    INDEX
    Explanations

    organizations and relationships

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

    The neuron strongly activates on words ending with the suffix “–ships.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    In
    -3.06
    Since
    -2.91
    With
    -2.77
    ?
    -2.73
    At
    -2.63
    If
    -2.59
    Not
    -2.58
    It
    -2.58
    an
    -2.58
    The
    -2.56
    POSITIVE LOGITS
    </strong>
    2.48
     ogrom
    2.44
     alojamientos
    2.36
    튿
    2.33
    
    2.33
    嚒
    2.33
    ⃑
    2.28
    archiwizowane
    2.28
    镡
    2.27
    すすめ
    2.25
    Activations Density 0.007%

    No Known Activations