© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 100682
    Prev
    Next
    INDEX
    Explanations

    belt, ride, strapped, ready

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

    The neuron fires on words and phrases related to buckling in or strapping safety belts (e.g., “seat,” “belt,” “strap,” “unbuckled,” “ride,” etc.).

    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
     khusus
    -1.50
     tocando
    -1.48
    /****
    -1.47
    '
    -1.47
     приез
    -1.45
    &
    -1.41
    _
    -1.36
     був
    -1.36
    ``
    -1.33
     beneficial
    -1.31
    POSITIVE LOGITS
    </i>
    1.82
    我們
    1.82
    上の
    1.74
    )}(
    1.72
    しました
    1.71
    AddHtmlAttribute
    1.60
    )]
    
    1.52
    __*/
    1.52
    peche
    1.51
    })\
    1.48
    Activations Density 0.013%

    No Known Activations