© 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. 23877
    Prev
    Next
    INDEX
    Explanations

    girl and variations

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

    The neuron fires strongly whenever the substring “girl” (often capitalized as “Girl”) appears in the 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
    s
    -3.23
    🡺
    -2.98
    但这
    -2.41
     insatiable
    -2.41
    但是在
    -2.41
    sandalia
    -2.39
    采用了
    -2.39
     meisten
    -2.34
     sprzedaży
    -2.31
    얗
    -2.27
    POSITIVE LOGITS
    .
    2.97
    就跟
    2.69
     This
    2.55
     dengan
    2.53
    out
    2.44
     vorigen
    2.44
     behulp
    2.38
    Your
    2.36
     Tonnen
    2.30
     schlechte
    2.28
    Activations Density 0.010%

    No Known Activations