© 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. 50486
    Prev
    Next
    INDEX
    Explanations

    descriptive clauses after punctuation

    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
     (!__
    -1.09
    你在
    -1.07
     encontrado
    -1.04
    لبة
    -1.02
     occidentalis
    -0.97
    šķ
    -0.96
     ソー
    -0.93
     suitable
    -0.91
     колле
    -0.91
     perdida
    -0.90
    POSITIVE LOGITS
     which
    3.13
     who
    2.88
     whose
    2.72
    whose
    1.93
     headquartered
    1.82
     whom
    1.74
    which
    1.71
     one
    1.59
     makers
    1.59
    who
    1.53
    Activations Density 0.100%

    No Known Activations