© 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. 69912
    Prev
    Next
    INDEX
    Explanations

    bring up information

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

    The neuron detects words or phrases that denote evoking or bringing something to mind (e.g. evoke, recall, conjure up).

    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
    </h5>
    -1.77
    )
    
    -1.77
    );
    
    -1.74
    :
    
    -1.66
    </h1>
    -1.63
    ;
    
    -1.59
    」 
    -1.54
     других
    -1.54
     =
    -1.52
    you
    -1.52
    POSITIVE LOGITS
     only
    1.71
    řízen
    1.69
     and
    1.63
    nowu
    1.50
     from
    1.44
     использованием
    1.42
     aquellas
    1.36
    指定
    1.34
    IDENTAL
    1.31
     titolata
    1.30
    Activations Density 0.085%

    No Known Activations