© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 45280
    Prev
    Next
    INDEX
    Explanations

    being following certain verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    去吧
    -1.16
    とのこと
    -1.13
     bereit
    -1.12
    上がった
    -1.12
     ,‬
    -1.10
     ergän
    -1.09
     a
    -1.09
     verantwort
    -1.05
     beteiligt
    -1.05
     saw
    -1.04
    POSITIVE LOGITS
     being
    6.41
    being
    4.06
     becoming
    3.42
     étant
    3.39
    Being
    3.31
     having
    3.30
     BEING
    3.09
     getting
    2.94
     Being
    2.84
     sendo
    2.67
    Activations Density 0.262%

    No Known Activations