© 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. 36499
    Prev
    Next
    INDEX
    Explanations

    boolean values

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

    The neuron detects literal Boolean values (e.g. the tokens “true” and “false”).

    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
     will
    -1.41
     of
    -1.30
     ibang
    -1.27
     in
    -1.22
    carolina
    -1.11
     just
    -1.08
     usually
    -1.07
     that
    -1.04
     buhay
    -1.03
     silang
    -1.03
    POSITIVE LOGITS
    țial
    1.23
    ÉM
    1.17
    :'#
    1.09
    )!
    1.06
     "");
    1.05
    !</
    1.05
    胳膊
    1.04
     Rashford
    1.03
     elke
    1.02
    ”!
    1.01
    Activations Density 0.001%

    No Known Activations