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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 685
    Prev
    Next
    INDEX
    Explanations

    past tense verbs and linking 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
     it
    -1.57
     or
    -1.57
    apé
    -1.41
     this
    -1.41
     being
    -1.39
     I
    -1.34
    ませんが
    -1.34
     them
    -1.27
     الأخرى
    -1.25
     knowing
    -1.23
    POSITIVE LOGITS
    几个人
    1.59
     jopa
    1.44
     indeed
    1.42
    днако
    1.41
    较为
    1.40
    ヂ
    1.40
     möjligt
    1.37
     pudieron
    1.35
     harán
    1.35
    
    1.34
    Activations Density 0.251%

    No Known Activations