© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 98995
    Prev
    Next
    INDEX
    Explanations

    file or permission to do something

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

    The neuron consistently lights up on core action verbs in their base (infinitive) form.

    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
     doable
    -1.10
     necesita
    -1.10
     to
    -1.06
     siempre
    -1.05
     alltid
    -1.05
    ensical
    -1.04
     srdce
    -1.04
    contentPadding
    -1.02
    >--}}
    -1.02
     надо
    -1.02
    POSITIVE LOGITS
     boletín
    1.35
     such
    1.32
     when
    1.26
    飆
    1.25
     desglose
    1.24
     congreso
    1.23
    でしたが
    1.20
     câteva
    1.15
     purchase
    1.14
     without
    1.13
    Activations Density 0.182%

    No Known Activations