© 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. 118326
    Prev
    Next
    INDEX
    Explanations

    resolving ending ambiguity

    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
     lutter
    -0.87
    sendLog
    -0.83
    étit
    -0.82
    arians
    -0.82
    uchtet
    -0.79
    later
    -0.79
     décrire
    -0.79
    casing
    -0.77
    県の
    -0.76
     LATER
    -0.76
    POSITIVE LOGITS
     cliff
    4.19
    cliff
    2.91
    Cliff
    2.50
     Cliff
    2.48
     cliffs
    2.03
     ending
    1.72
     cli
    1.62
     dangling
    1.52
     leaving
    1.52
     Cliffs
    1.49
    Activations Density 0.016%

    No Known Activations