© 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. 10-GEMMASCOPE-RES-131K
    7. 111034
    Prev
    Next
    INDEX
    Explanations

    past tense 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_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
     was
    -2.05
     were
    -2.03
     when
    -1.54
     didn
    -1.41
     to
    -1.36
     attempts
    -1.35
     weren
    -1.27
    corpions
    -1.26
     wasn
    -1.23
    ceptre
    -1.23
    POSITIVE LOGITS
    찮
    1.35
     робити
    1.28
     retour
    1.25
    ❑
    1.23
    О
    1.23
     ambao
    1.22
    Ŭ
    1.19
    ТП
    1.17
    Flow
    1.17
    ✱
    1.16
    Activations Density 0.139%

    No Known Activations