© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26
    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 79218
    Prev
    Next
    INDEX
    Explanations

    statistics, names, volunteers

    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
     abgerufen
    -1.03
     for
    -1.01
     this
    -0.97
    )+
    -0.96
     \\
    -0.94
     Hersteller
    -0.88
     create
    -0.88
     verdieping
    -0.88
    飲む
    -0.85
     \""
    -0.84
    POSITIVE LOGITS
     cuadrados
    1.10
    </strong>
    1.09
    quelize
    1.08
     indes
    1.07
    Recep
    1.06
    </th>
    1.06
    ában
    1.04
    Recept
    1.00
    Giới
    0.99
    Forsch
    0.99
    Activations Density 0.000%

    No Known Activations