© 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. 34-GEMMASCOPE-RES-131K
    4. 107247
    Prev
    Next
    INDEX
    Explanations

    ease of use and action

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

    The neuron responds to user-oriented action words—like “use,” “install,” “make,” “clean,” “customize,” etc.—especially in contexts emphasizing that these tasks are easy or trivial.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     to
    -1.63
    際に
    -1.44
     of
    -1.13
    あく
    -1.10
    すっ
    -1.09
    なるべく
    -1.08
     возможно
    -1.05
     höchst
    -1.02
    為に
    -1.02
     это
    -1.02
    POSITIVE LOGITS
     and
    2.06
     compared
    1.51
     even
    1.48
     because
    1.42
    compared
    1.36
     навіть
    1.34
     yourself
    1.23
     with
    1.21
     especially
    1.16
     anywhere
    1.16
    Activations Density 0.032%

    No Known Activations