© 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. 73125
    Prev
    Next
    INDEX
    Explanations

    if clauses

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

    The neuron activates on the conditional word “if,” marking the start of an “if” clause.

    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
    引用元
    -1.66
    　　　　　　
    -1.50
     abbraccio
    -1.48
     organizador
    -1.47
     buon
    -1.47
     ͡
    -1.46
     стекла
    -1.46
    𝙇
    -1.45
    ：[
    -1.45
    ſten
    -1.45
    POSITIVE LOGITS
    f
    1.97
    si
    1.74
    -
    1.69
     be
    1.66
    </strong>
    1.63
    p
    1.63
     But
    1.60
    h
    1.59
    li
    1.56
    x
    1.56
    Activations Density 0.027%

    No Known Activations