© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 34954
    Prev
    Next
    INDEX
    Explanations

    prepositional phrases about nature and location

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

    descriptions of animal movement or migration patterns in their natural habitats.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron strongly activates on the word “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_22/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
    ּוֹ
    -1.31
    ־ה
    -1.28
     Geistes
    -1.24
    ==""){
    -1.24
     خریدار
    -1.23
    וֹ
    -1.23
     бампер
    -1.23
     موبایل
    -1.23
     تلفن
    -1.21
     especialidad
    -1.20
    POSITIVE LOGITS
     their
    2.28
    ׇ
    1.63
     they
    1.52
     during
    1.52
     ویتامین
    1.44
    their
    1.35
     themselves
    1.30
     thier
    1.29
    อร่อย
    1.29
    rosso
    1.22
    Activations Density 0.031%

    No Known Activations