© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 102417
    Prev
    Next
    INDEX
    Explanations

    what to expect if

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

    The neuron activates on occurrences of the word “expect” (in any form or casing).

    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
     refroid
    -2.09
    越來
    -1.83
    %;
    
    -1.74
     черные
    -1.72
     obiet
    -1.67
    냑
    -1.66
     giocatore
    -1.65
    </sub>
    -1.65
    ;}
    
    -1.63
     votre
    -1.61
    POSITIVE LOGITS
     of
    2.34
     in
    1.91
     from
    1.69
     while
    1.66
     with
    1.65
    0
    1.60
     if
    1.51
    8
    1.50
     or
    1.49
     مختلفة
    1.48
    Activations Density 0.012%

    No Known Activations