© 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. 330
    Prev
    Next
    INDEX
    Explanations

    field of the invention

    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
    herit
    -0.81
    ){$
    -0.80
     Robbins
    -0.78
     Pacers
    -0.77
     çek
    -0.75
     Brink
    -0.75
     CREATE
    -0.74
    zubauen
    -0.74
     Casting
    -0.73
    rint
    -0.72
    POSITIVE LOGITS
    Jud
    0.77
    reeg
    0.71
     working
    0.71
    ouss
    0.70
     Zeno
    0.70
    Until
    0.68
    ponents
    0.67
    rgb
    0.66
     id
    0.66
    렸
    0.66
    Activations Density 0.030%

    No Known Activations