© 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. 10-GEMMASCOPE-RES-131K
    7. 11518
    Prev
    Next
    INDEX
    Explanations

    CD player, CD drive, CD changer

    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_10/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
    O
    -2.45
    {~
    -2.27
    medriver
    -2.13
    1
    -2.09
    ⸥
    -2.06
    愎
    -2.00
    зика
    -1.97
     they
    -1.97
    魠
    -1.97
    𖣘
    -1.95
    POSITIVE LOGITS
     This
    2.61
     It
    2.34
    玙
    2.22
     мы
    2.14
    vaný
    2.09
    owany
    1.99
     Our
    1.92
    握手
    1.91
    ?!?
    1.86
    л
    1.84
    Activations Density 0.026%

    No Known Activations