© 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. 31542
    Prev
    Next
    INDEX
    Explanations

    Savannah Georgia

    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
     Acho
    -0.75
    мя
    -0.71
     ferret
    -0.69
    Contract
    -0.69
     obsidian
    -0.68
    itens
    -0.68
     Bibliothek
    -0.67
    烴
    -0.67
     serii
    -0.67
    Yun
    -0.67
    POSITIVE LOGITS
     Savannah
    1.80
    Savannah
    1.47
     Chatham
    1.16
    avannah
    1.11
     Georgia
    0.94
     savannah
    0.93
     Thunderbolt
    0.92
    SAV
    0.84
     Ogle
    0.83
     Sav
    0.77
    Activations Density 0.022%

    No Known Activations