© 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. 19803
    Prev
    Next
    INDEX
    Explanations

    it seems like

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

    This neuron responds to occurrences of the hedging phrase “seems (like).”

    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
    n
    -2.69
    k
    -2.31
    l
    -2.31
    );
    -2.28
    o
    -2.19
     He
    -2.09
    We
    -2.06
    It
    -2.02
    c
    -1.98
    b
    -1.98
    POSITIVE LOGITS
    湏
    2.02
    satunya
    2.00
    衚
    1.99
    ൪
    1.84
    鋱
    1.84
     AFFAIRS
    1.83
    跣
    1.83
     ſame
    1.83
     combatt
    1.80
    缑
    1.80
    Activations Density 0.009%

    No Known Activations