© 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. 59718
    Prev
    Next
    INDEX
    Explanations

    stepping forward

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

    The neuron detects words and phrases that signal advancing or volunteering—most strongly “forward” and its variants (e.g. “step up,” “stepped forward”).

    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
    (
    -2.13
    in
    -2.03
    *
    -1.91
    '
    -1.81
        
    -1.72
          
    -1.71
    "
    -1.71
    3
    -1.68
       
    -1.68
    .
    -1.65
    POSITIVE LOGITS
     valentín
    2.00
    ܇
    1.96
     parachoque
    1.80
    CHREIB
    1.76
     広場
    1.74
    沨
    1.68
    ꪻ
    1.67
    淠
    1.65
     jeruk
    1.63
    
    1.63
    Activations Density 0.008%

    No Known Activations