© 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. 98034
    Prev
    Next
    INDEX
    Explanations

    video output components

    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
     cashew
    -0.84
    ofu
    -0.77
     ABR
    -0.76
     hearing
    -0.75
     Oly
    -0.75
     embers
    -0.74
    zón
    -0.74
    anko
    -0.74
     comando
    -0.73
    IMM
    -0.73
    POSITIVE LOGITS
     composite
    1.71
     Composite
    1.68
    Composite
    1.52
    composite
    1.48
     Component
    1.27
     component
    1.18
     video
    1.16
     output
    1.14
     COMPOS
    1.13
     composites
    1.11
    Activations Density 0.026%

    No Known Activations