Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8560
    Prev
    Next
    INDEX
    Explanations

    has + past participle

    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
    iferous
    -1.09
     fiind
    -1.05
    ’
    -1.02
    เพราะ
    -1.02
    ebly
    -1.02
    搧
    -0.99
    alamualaikum
    -0.98
    because
    -0.98
    理
    -0.98
    inerario
    -0.98
    POSITIVE LOGITS
     been
    3.08
     its
    2.02
     to
    1.80
     become
    1.69
     not
    1.59
     always
    1.57
     proven
    1.45
     never
    1.36
     gotta
    1.30
     recently
    1.29
    Activations Density 0.108%

    No Known Activations