© 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. 66593
    Prev
    Next
    INDEX
    Explanations

    trying to figure out

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

    The neuron fires strongly on the words “figure out,” i.e. the phrase expressing an attempt to determine or solve something.

    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
    %;
    
    -1.60
     многих
    -1.52
     Handlungen
    -1.51
     Erfüllung
    -1.42
    If
    -1.41
    ኗ
    -1.37
    
    -1.30
     Когда
    -1.27
    为您
    -1.26
     erforderlichen
    -1.26
    POSITIVE LOGITS
     which
    1.80
     hemd
    1.41
    Salz
    1.30
     geene
    1.30
     itinéraires
    1.28
     êtres
    1.27
    
    1.27
     geel
    1.25
     a
    1.24
     of
    1.24
    Activations Density 0.074%

    No Known Activations