© 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. 60879
    Prev
    Next
    INDEX
    Explanations

    McKellar, Hallmark, Lifetime movies

    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
    江南
    -0.90
    IAC
    -0.78
    🚀
    -0.76
     речо
    -0.73
    セブン
    -0.73
     PROC
    -0.71
     NVIDIA
    -0.71
     phenomenal
    -0.71
     hydroxide
    -0.71
     Middlesex
    -0.70
    POSITIVE LOGITS
     Hallmark
    1.42
    Lifetime
    1.19
     Lifetime
    1.16
     HALL
    1.12
    Hall
    1.07
    lifetime
    0.97
     hallmark
    0.96
     movies
    0.96
     Movies
    0.92
     movie
    0.85
    Activations Density 0.013%

    No Known Activations