© 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. 99565
    Prev
    Next
    INDEX
    Explanations

    action verbs followed by nouns

    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
     like
    -1.63
     when
    -1.57
     persönliche
    -1.41
    ご馳走
    -1.32
     blaue
    -1.30
    oléon
    -1.29
     mögliche
    -1.23
     montrer
    -1.23
     although
    -1.23
    iglie
    -1.20
    POSITIVE LOGITS
     and
    1.44
     简介
    1.20
     封面
    1.18
    efter
    1.16
    pids
    1.16
    Sufficient
    1.16
    KindOfClass
    1.15
    komplet
    1.13
    Jueves
    1.11
    wwwww
    1.11
    Activations Density 0.155%

    No Known Activations