© 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. 107947
    Prev
    Next
    INDEX
    Explanations

    place names and administrative divisions

    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
     also
    -1.08
     here
    -0.94
     get
    -0.87
     find
    -0.83
     außerdem
    -0.82
     alleviate
    -0.81
    ྕ
    -0.81
     rangka
    -0.80
    ↵↵↵
    -0.76
     not
    -0.76
    POSITIVE LOGITS
    Estos
    0.97
    Madre
    0.97
    educt
    0.93
     Ärz
    0.92
     koment
    0.92
    SetOutput
    0.91
    ervative
    0.91
    sibly
    0.91
    !“
    0.90
    Descargar
    0.90
    Activations Density 0.090%

    No Known Activations