© 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. 22-GEMMASCOPE-RES-131K
    7. 27905
    Prev
    Next
    INDEX
    Explanations

    beings becoming

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

    The neuron strongly activates on past-tense verb forms (including auxiliaries and participles).

    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
     they
    -1.85
     it
    -1.42
     that
    -1.37
     their
    -1.32
    <bos>
    -1.27
     thier
    -1.27
     jejich
    -1.24
     Their
    -1.18
     вона
    -1.14
     sowie
    -1.13
    POSITIVE LOGITS
     himself
    2.38
    himself
    1.73
     his
    1.48
    lllllll
    1.40
    llllll
    1.39
    !(:
    1.29
     خودش
    1.29
    刧
    1.25
    おわりに
    1.24
    lllllllll
    1.23
    Activations Density 0.118%

    No Known Activations