© 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. 40314
    Prev
    Next
    INDEX
    Explanations

    no limits or bounds

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

    The neuron fires on absolute or universal quantifiers and negations—words like “whatever,” “nothing,” “no,” “any,” etc., that express totality or absoluteness.

    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
     drá
    -0.95
     Şi
    -0.86
    Ⓚ
    -0.82
    odine
    -0.81
     jogadores
    -0.81
    𝑿
    -0.80
    Bilder
    -0.80
     vols
    -0.80
    ǘ
    -0.79
    Hou
    -0.79
    POSITIVE LOGITS
     anything
    1.26
     anywhere
    1.25
     Anything
    1.16
    Anything
    1.11
     limits
    1.05
     conceivable
    1.04
     limit
    1.04
     bounds
    0.93
     everything
    0.92
     practically
    0.90
    Activations Density 0.028%

    No Known Activations