© 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. 100911
    Prev
    Next
    INDEX
    Explanations

    causation and enablement

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

    The neuron fires strongly on causative or enabling verbs (e.g. provide, make, lead, allow) commonly used to describe effects or mechanisms.

    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
     on
    -1.80
     to
    -1.72
     in
    -1.68
     who
    -1.55
     as
    -1.46
    comings
    -1.40
    мере
    -1.32
    🙋
    -1.31
     uska
    -1.31
    РЫ
    -1.30
    POSITIVE LOGITS
     decoracion
    1.76
     árbitro
    1.73
     pozwala
    1.73
    colgante
    1.69
     Schluß
    1.66
    </h4>
    1.66
    擽
    1.66
    Boletín
    1.63
     zdecydow
    1.63
    Another
    1.60
    Activations Density 0.129%

    No Known Activations