© 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. 22-GEMMASCOPE-RES-131K
    4. 70592
    Prev
    Next
    INDEX
    Explanations

    if not

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

    The neuron detects the phrase “if not” (i.e. “if not X”) as a linguistic intensifier or exception marker.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    えっ
    -1.62
    まさかの
    -1.58
    いかがでしたか
    -1.54
    を買う
    -1.42
     this
    -1.41
    ・・・・・・・・
    -1.40
     these
    -1.40
    じゃなくて
    -1.35
    >>
    -1.34
     such
    -1.33
    POSITIVE LOGITS
     también
    1.45
    Also
    1.32
     also
    1.32
    We
    1.30
    rewsbury
    1.22
    w
    1.22
     U
    1.20
     juga
    1.20
    也
    1.19
     The
    1.18
    Activations Density 0.006%

    No Known Activations