© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 116095
    Prev
    Next
    INDEX
    Explanations

    first

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/gemma-4-saes/gemma-4-31b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     प्रवेश
    -0.06
     інші
    -0.06
    !,
    -0.06
     специальных
    -0.05
     другие
    -0.05
     інших
    -0.05
    У
    -0.05
     inset
    -0.05
    Hover
    -0.05
    ంచి
    -0.05
    POSITIVE LOGITS
     first
    0.08
     primeiro
    0.07
     primero
    0.07
     ആദ്യം
    0.07
     eerste
    0.07
     první
    0.06
     የመጀመሪያ
    0.06
     Lords
    0.06
    something
    0.06
     पंड
    0.06
    Activations Density 0.001%

    No Known Activations