© 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. 12452
    Prev
    Next
    INDEX
    Explanations

    "guys" + modal verbs/intent

    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
    -2.53
     each
    -2.11
     Regardless
    -1.71
     where
    -1.68
     with
    -1.68
     when
    -1.66
    纒
    -1.62
     but
    -1.59
     during
    -1.58
     because
    -1.56
    POSITIVE LOGITS
    ‘‘
    2.00
    perhaps
    2.00
    possibly
    1.90
    didn
    1.90
     ‘‘
    1.88
     ensuing
    1.84
    ’’
    1.81
     startling
    1.79
     ᾿
    1.73
     educativos
    1.72
    Activations Density 0.005%

    No Known Activations