© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 70428
    Prev
    Next
    INDEX
    Explanations

    i'd like to

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

    the phrase “like to” (as in “I’d like to…”), marking user requests or expressions of desire.

    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
    If
    -1.72
    .
    -1.66
    S
    -1.64
    It
    -1.62
     tne
    -1.55
    ;
    -1.54
    k
    -1.52
    𓋼
    -1.51
    t
    -1.51
    Of
    -1.48
    POSITIVE LOGITS
     they
    1.82
     \'
    1.80
    ܸ
    1.70
    parque
    1.67
     keduanya
    1.63
     said
    1.59
     estén
    1.55
    
    1.52
     encontramos
    1.52
     we
    1.51
    Activations Density 0.021%

    No Known Activations