© 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. 59757
    Prev
    Next
    INDEX
    Explanations

    verses, stanzas, and song lyrics

    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
     Trajectory
    -0.75
    grammar
    -0.75
    Gesture
    -0.72
    ⣰
    -0.71
     دریافت
    -0.71
     secure
    -0.71
    PEM
    -0.71
    yelidikan
    -0.69
     круг
    -0.68
    نامه
    -0.67
    POSITIVE LOGITS
     verses
    2.31
     verse
    2.25
     stanza
    1.71
     stanzas
    1.61
    verse
    1.42
     Verse
    1.38
     Verses
    1.32
     quat
    1.30
    verses
    1.27
    Verse
    1.24
    Activations Density 0.029%

    No Known Activations