© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 117131
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     môi
    -0.07
     प्रणाम
    -0.06
    做到
    -0.06
    鋆
    -0.06
    ම්
    -0.06
    私たち
    -0.06
     Affected
    -0.06
     hindered
    -0.06
    阻止
    -0.06
     由于
    -0.06
    POSITIVE LOGITS
     …,
    0.06
    nh
    0.06
     from
    0.06
     (=
    0.06
    $%
    0.05
    …,
    0.05
     POW
    0.05
    oslash
    0.05
     accessible
    0.05
    彼の
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.