© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 12499
    Prev
    Next
    INDEX
    Explanations

    family and friends

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

    The neuron fires on mentions of “friend” (or “friends”) in the 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_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
     stratég
    -1.53
     koš
    -1.52
    噲
    -1.46
    
    -1.45
     női
    -1.45
    días
    -1.43
     nyel
    -1.42
    鏷
    -1.42
     zdra
    -1.41
     kár
    -1.40
    POSITIVE LOGITS
     who
    1.73
    </td>
    1.55
    ’’
    1.47
    %
    1.47
     &
    1.44
    <h2>
    1.34
    geſ
    1.33
    },
    1.30
     hänen
    1.30
    Bad
    1.28
    Activations Density 0.048%

    No Known Activations