© 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. 63169
    Prev
    Next
    INDEX
    Explanations

    island names

    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
     pesada
    -1.02
     Ibidem
    -0.97
     ورز
    -0.95
     Opportun
    -0.93
     仕様
    -0.89
     áreas
    -0.88
     チラシ
    -0.88
     ovp
    -0.88
     multiuso
    -0.88
     трябва
    -0.87
    POSITIVE LOGITS
     Island
    1.96
     island
    1.78
    岛
    1.41
    島
    1.34
    Island
    1.30
     Islands
    1.21
    island
    1.04
     ISLAND
    1.04
     islands
    0.95
     Off
    0.94
    Activations Density 0.032%

    No Known Activations