© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 433
    Prev
    Next
    INDEX
    Explanations

    coast and border locations

    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
    縢
    -0.91
     horrible
    -0.91
     secluded
    -0.91
    řad
    -0.91
     GOtt
    -0.90
     extremely
    -0.90
     ottima
    -0.86
     miesto
    -0.85
     significantly
    -0.81
     costante
    -0.81
    POSITIVE LOGITS
     of
    2.00
    line
    1.34
     line
    1.28
    🌲
    1.06
     where
    1.06
     Abgerufen
    1.00
    lines
    0.97
    ☀️
    0.94
     at
    0.94
    lijn
    0.94
    Activations Density 0.061%

    No Known Activations