© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 9534
    Prev
    Next
    INDEX
    Explanations

    managing and modifying states

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

    The neuron responds strongly to present-tense action verbs that denote intervening, modifying, controlling, or improving something.

    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
     wszystkich
    -1.02
     unveils
    -0.99
    ampilan
    -0.98
    הם
    -0.94
     fulf
    -0.94
     promise
    -0.93
    ุทธ
    -0.93
     rígido
    -0.93
     trzech
    -0.93
    的他
    -0.91
    POSITIVE LOGITS
     it
    1.18
     about
    1.17
     Extremely
    1.05
     There
    1.05
     what
    1.03
     Probably
    1.02
     Amazing
    1.02
     Schließlich
    1.02
     المعيار
    1.01
     probably
    1.00
    Activations Density 0.237%

    No Known Activations