© 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. 59819
    Prev
    Next
    INDEX
    Explanations

    Sure, surely

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

    The neuron fires on instances of the word “sure” (and its variants like “surely”) used to open or affirmively respond in text.

    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
    CGRectMake
    -1.80
     моделей
    -1.76
    .],
    -1.73
     singola
    -1.70
    ︱
    -1.70
    +]
    -1.65
    +:
    -1.63
    úcia
    -1.60
     probabilmente
    -1.58
    atória
    -1.57
    POSITIVE LOGITS
     WHAT
    1.75
    no
    1.65
     technically
    1.63
    co
    1.60
    ll
    1.59
    actéristi
    1.57
    ⟞
    1.52
    to
    1.48
    莲花
    1.45
    as
    1.45
    Activations Density 0.003%

    No Known Activations