© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49617
    Prev
    Next
    INDEX
    Explanations

    geography and fat/cell

    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
     chrétienne
    -0.94
     DIAGRAM
    -0.84
    resultSet
    -0.84
     CGRect
    -0.81
     Octobre
    -0.81
    媚
    -0.80
    ประมาณ
    -0.79
    Una
    -0.79
     newInstance
    -0.78
     identificado
    -0.77
    POSITIVE LOGITS
     [
    1.18
     cursive
    0.82
    都被
    0.82
    Tarjeta
    0.81
     ARISING
    0.80
    onii
    0.79
     projec
    0.79
    lavia
    0.79
    Ryo
    0.77
     extro
    0.77
    Activations Density 0.005%

    No Known Activations