© 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. 57284
    Prev
    Next
    INDEX
    Explanations

    organized, sponsored, hosted events

    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
    Completed
    -0.79
    StringValue
    -0.79
    BuildConfig
    -0.78
    athed
    -0.78
    шина
    -0.77
    ellyn
    -0.77
     Chor
    -0.77
     molho
    -0.75
     situés
    -0.75
    needed
    -0.75
    POSITIVE LOGITS
     organized
    4.34
     organised
    4.03
     sponsored
    3.56
    organized
    3.45
     hosted
    3.41
    Organized
    3.33
     Organized
    3.27
     органи
    3.09
     organizado
    3.08
     organizada
    2.88
    Activations Density 0.110%

    No Known Activations