© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 32509
    Prev
    Next
    INDEX
    Explanations

    film scribe or director

    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
     comedy
    -1.10
    罰
    -0.88
    caric
    -0.79
    专属
    -0.79
     различни
    -0.79
    取决
    -0.79
    nadores
    -0.78
    ୁ
    -0.77
     comedia
    -0.76
     comedies
    -0.75
    POSITIVE LOGITS
     tolle
    0.79
    ДД
    0.76
    森林
    0.76
    ﻤ
    0.75
    Nar
    0.75
    兄弟
    0.74
     Kodi
    0.74
    kur
    0.74
    cribed
    0.73
    提
    0.73
    Activations Density 0.039%

    No Known Activations