© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 33721
    Prev
    Next
    INDEX
    Explanations

    constant ongoing situations

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

    The neuron primarily detects occurrences of the word “constant” (including forms like “constantly”).

    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
    始めて
    -1.60
    瘣
    -1.45
    zugehen
    -1.45
    时的
    -1.43
     pakan
    -1.42
     already
    -1.40
    蜴
    -1.32
    但在
    -1.30
    Inscription
    -1.30
    simpan
    -1.30
    POSITIVE LOGITS
    It
    1.48
    ;
    
    1.45
     You
    1.43
     They
    1.41
    constant
    1.40
    get
    1.37
    m
    1.34
     $
    1.31
    Constant
    1.31
    ine
    1.30
    Activations Density 0.048%

    No Known Activations