© 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. 118172
    Prev
    Next
    INDEX
    Explanations

    `province` `Provin` `provin` `9` `/*` `Archives` `Q` `Universal` `Ap`

    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
    Arguments
    -1.09
     Arguments
    -0.90
     י
    -0.84
    arguments
    -0.83
    多
    -0.81
    getBounds
    -0.80
    Server
    -0.79
    ٓ
    -0.79
    BO
    -0.79
    ();
    -0.78
    POSITIVE LOGITS
    province
    0.91
     DCC
    0.90
    Klik
    0.89
    provin
    0.89
    affiche
    0.86
     RUD
    0.86
    Provin
    0.85
     REVOLUTION
    0.85
     provinces
    0.85
     meubles
    0.85
    Activations Density 0.007%

    No Known Activations