© 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. 65356
    Prev
    Next
    INDEX
    Explanations

    the phrase "not all"

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

    This neuron detects the word “all” when it appears in negated phrases (e.g. “not all …”).

    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
    这般
    -2.05
    ﻂ
    -1.96
     zvuky
    -1.92
    ⨳
    -1.88
     tels
    -1.79
    issory
    -1.75
    vège
    -1.72
     saute
    -1.68
     condos
    -1.66
     estadía
    -1.64
    POSITIVE LOGITS
     of
    2.20
    The
    2.05
     will
    2.03
    “
    1.66
    <em>
    1.65
    ра
    1.65
    ：……
    1.64
     could
    1.60
     always
    1.59
    and
    1.59
    Activations Density 0.004%

    No Known Activations