© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 56058
    Prev
    Next
    INDEX
    Explanations

    highlights and details

    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
    quakes
    -0.98
     tremor
    -0.87
    を重ね
    -0.82
     girar
    -0.82
    stylers
    -0.78
     sonido
    -0.76
     Twp
    -0.76
     ANNUAL
    -0.76
    生徒
    -0.75
     SEND
    -0.75
    POSITIVE LOGITS
     highlights
    1.37
     Highlights
    1.33
    highlights
    1.15
    Highlights
    1.14
     highlight
    1.09
     Detail
    1.08
     Highlight
    1.05
    Highlight
    1.02
     detail
    0.99
     rendition
    0.98
    Activations Density 0.031%

    No Known Activations