© 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. 128983
    Prev
    Next
    INDEX
    Explanations

    promises and actions

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

    The neuron fires strongly on base‐form verbs appearing in infinitival to-phrases (i.e. verbs following “to”).

    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
    Why
    -1.39
     něj
    -1.35
     cambiar
    -1.30
    Those
    -1.30
     sufrir
    -1.29
     poprzez
    -1.28
     estos
    -1.26
     nedeniyle
    -1.26
     obligado
    -1.23
     desnuda
    -1.23
    POSITIVE LOGITS
     when
    1.73
     specta
    1.50
     pernic
    1.38
     tatt
    1.30
     лишь
    1.30
     then
    1.27
     tricot
    1.27
    货
    1.27
     cil
    1.25
     trev
    1.25
    Activations Density 0.036%

    No Known Activations