© 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. 120928
    Prev
    Next
    INDEX
    Explanations

    full path or qualified name

    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
    Negative Logits
    いを
    -0.06
     or
    -0.06
     또는
    -0.06
     arise
    -0.06
     എന്റെ
    -0.06
     ஓர்
    -0.06
    または
    -0.06
     reach
    -0.06
     expose
    -0.06
     કર્યો
    -0.06
    POSITIVE LOGITS
     bit
    0.06
    substack
    0.06
     सत्या
    0.06
    header
    0.06
    heading
    0.05
     रख
    0.05
     outro
    0.05
     другому
    0.05
    ได้
    0.05
    not
    0.05
    Activations Density 0.005%

    No Known Activations