© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 92694
    Prev
    Next
    INDEX
    Explanations

    video and audio technology terms

    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
     cyto
    -0.89
     RFID
    -0.88
    ubble
    -0.82
    磁盘
    -0.81
     fondos
    -0.81
     salmón
    -0.80
     DVI
    -0.79
    SVN
    -0.78
    🙀
    -0.78
    textra
    -0.77
    POSITIVE LOGITS
     HDR
    1.64
     metadata
    1.20
    HDR
    1.10
     Metadata
    1.05
     Dolby
    1.00
    metadata
    0.99
    MetaData
    0.97
     Atmos
    0.97
     hdr
    0.94
     content
    0.90
    Activations Density 0.007%

    No Known Activations