© 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. 108928
    Prev
    Next
    INDEX
    Explanations

    CS errors and introduction

    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
     İç
    -0.87
     kijken
    -0.87
     também
    -0.86
    帖最后由
    -0.83
     souhaitez
    -0.82
     también
    -0.82
    心态
    -0.82
     máte
    -0.81
     shaping
    -0.81
    </h1>
    -0.81
    POSITIVE LOGITS
     field
    1.10
    sedia
    1.02
    Ανα
    0.93
    field
    0.90
     میدان
    0.87
     nong
    0.85
    Fields
    0.84
     Unger
    0.82
    Field
    0.82
     Bahkan
    0.82
    Activations Density 0.004%

    No Known Activations