© 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. 90036
    Prev
    Next
    INDEX
    Explanations

    jdbc and Inc

    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
    Ὅ
    -0.73
     poplar
    -0.73
    Andra
    -0.69
    ינו
    -0.69
     بلکه
    -0.68
     íntegra
    -0.68
    OVERN
    -0.67
    去除
    -0.67
    債
    -0.66
    حية
    -0.65
    POSITIVE LOGITS
    ril
    0.79
    :%
    0.77
     Bia
    0.73
     Miguel
    0.71
     Fj
    0.70
     Hurley
    0.69
    Miguel
    0.68
     essays
    0.68
     utrzy
    0.68
    Bia
    0.65
    Activations Density 0.060%

    No Known Activations