© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 2167
    Prev
    Next
    INDEX
    Explanations

    code symbols and identifiers

    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
     etiam
    -0.82
     Pasquale
    -0.81
    SOUNDBITE
    -0.79
     Tất
    -0.79
     Systems
    -0.78
     وَ
    -0.78
    aną
    -0.76
    
    -0.75
     "*.
    -0.73
    ﻊ
    -0.73
    POSITIVE LOGITS
    Karakter
    0.87
    Ingredi
    0.84
    gelijke
    0.84
     Atlántico
    0.84
     doux
    0.82
    र्व
    0.82
     rahat
    0.78
    shadows
    0.78
     şek
    0.77
    ismer
    0.77
    Activations Density 0.011%

    No Known Activations