© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 104712
    Prev
    Next
    INDEX
    Explanations

    be + 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_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
    𓋼
    -2.44
    巨大的
    -2.28
    汌
    -2.25
    鼕
    -2.23
    戇
    -2.17
    ("
    -2.13
    )"
    -2.08
     और
    -2.06
    天的
    -2.05
     главный
    -2.05
    POSITIVE LOGITS
     They
    2.50
     However
    2.44
     be
    2.31
     we
    2.30
    ’
    2.20
     You
    2.19
     Unfortunately
    2.09
    ating
    2.08
     هناك
    2.06
     But
    2.00
    Activations Density 0.044%

    No Known Activations