© 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. 57834
    Prev
    Next
    INDEX
    Explanations

    Malaysian/Indonesian place 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
    Yale
    -0.77
    ちゃん
    -0.76
    cidas
    -0.74
     abus
    -0.73
     inal
    -0.73
     アート
    -0.71
    Palmarès
    -0.71
     extrapolation
    -0.70
     prepara
    -0.69
    结语
    -0.69
    POSITIVE LOGITS
     Hence
    0.80
    eltjes
    0.79
    Proof
    0.77
     marcó
    0.77
     帶
    0.77
     envejec
    0.75
     Proof
    0.75
    opensource
    0.75
    Even
    0.74
     discussing
    0.74
    Activations Density 0.008%

    No Known Activations