© 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. 472
    Prev
    Next
    INDEX
    Explanations

    selected, simplified, reduced, proposed

    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
     Parce
    -1.06
     antik
    -1.06
     tráfico
    -1.02
     harap
    -1.02
    batasan
    -1.02
     favoris
    -1.01
     obti
    -1.01
     sportif
    -1.00
     Lég
    -0.98
     هر
    -0.98
    POSITIVE LOGITS
     selected
    1.22
     simplified
    1.08
     distintas
    1.06
     reduced
    1.03
     proposed
    1.01
    atola
    1.00
    <eos>
    0.99
     and
    0.98
     doppelt
    0.98
     fiyatları
    0.96
    Activations Density 0.004%

    No Known Activations