© 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. 22-GEMMASCOPE-RES-131K
    4. 95620
    Prev
    Next
    INDEX
    Explanations

    return redirect, view, or json

    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_22/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
    ఙ
    -1.15
     katun
    -1.11
     keramik
    -1.11
    лябин
    -1.11
     kabar
    -1.10
    licken
    -1.10
     Meksi
    -1.07
     harap
    -1.07
     kapan
    -1.05
    
    -1.05
    POSITIVE LOGITS
    1.25
     back
    1.14
     an
    1.07
     вообще
    1.05
     ולא
    1.04
     at
    1.02
     when
    1.02
    (
    1.01
     fairly
    1.01
     rather
    1.01
    Activations Density 0.001%

    No Known Activations