© 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. 118276
    Prev
    Next
    INDEX
    Explanations

    academic subjects in courses

    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
     limitaciones
    -0.92
    Біографія
    -0.85
     admiten
    -0.85
     längere
    -0.85
     Leistungen
    -0.84
     imposto
    -0.84
    OuterClass
    -0.82
    以來
    -0.82
     Resmi
    -0.81
     bekannte
    -0.81
    POSITIVE LOGITS
     II
    2.05
     for
    1.57
     III
    1.42
     with
    1.23
    II
    1.22
     course
    1.08
     \&
    1.05
    Ⅰ
    1.05
     and
    1.01
     &
    0.97
    Activations Density 0.031%

    No Known Activations