© 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. 63585
    Prev
    Next
    INDEX
    Explanations

    software licenses and product descriptions

    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
     roman
    -0.77
     fiberglass
    -0.77
     capitalize
    -0.75
     имму
    -0.75
     Sketch
    -0.75
     nylon
    -0.75
     Vecchio
    -0.75
    런
    -0.75
    日起
    -0.75
    žių
    -0.74
    POSITIVE LOGITS
     MPEG
    0.97
    NAB
    0.96
     FILM
    0.96
    printk
    0.96
     ITU
    0.92
    MPEG
    0.91
    Cine
    0.91
     Harman
    0.91
     Video
    0.90
     Dolby
    0.89
    Activations Density 0.020%

    No Known Activations