© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 112457
    Prev
    Next
    INDEX
    Explanations

    anticipating actions

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

    This neuron consistently highlights the main action verbs (the key content verbs) in each sentence.

    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
     cantora
    -1.44
     atriz
    -1.37
     entschieden
    -1.20
    dzić
    -1.18
     willing
    -1.13
    Ҩ
    -1.11
     aufmerksam
    -1.09
    prende
    -1.07
     mejorar
    -1.07
     better
    -1.06
    POSITIVE LOGITS
    mathrm
    1.35
     misma
    1.32
    </b>
    1.27
    aneously
    1.26
     mismo
    1.23
    their
    1.17
    ját
    1.17
    šanas
    1.17
     sobie
    1.17
     at
    1.16
    Activations Density 0.130%

    No Known Activations