© 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. 73419
    Prev
    Next
    INDEX
    Explanations

    to permitwrite fractures

    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
    平
    -0.70
    эф
    -0.68
     יהיה
    -0.68
    ètes
    -0.68
    盖
    -0.66
    MASTER
    -0.65
    niejszy
    -0.65
    𝔭
    -0.64
    AILED
    -0.63
    석
    -0.63
    POSITIVE LOGITS
     Horatio
    0.74
     implement
    0.71
     implemented
    0.66
    categoryId
    0.66
    qe
    0.66
     ClassNotFound
    0.66
     ombre
    0.65
     zapewnia
    0.65
     Hügel
    0.64
    System
    0.63
    Activations Density 0.072%

    No Known Activations