© 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. 116137
    Prev
    Next
    INDEX
    Explanations

    get stuck or incorrect answer

    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
     sogenannten
    -0.06
     확대
    -0.06
     predsjed
    -0.06
     рис
    -0.06
     erweit
    -0.06
     étend
    -0.06
     fostering
    -0.06
     extending
    -0.06
     cosidd
    -0.06
     ఉత్ప
    -0.06
    POSITIVE LOGITS
     worked
    0.08
     был
    0.07
     finish
    0.07
     was
    0.07
     wrongly
    0.07
     finishes
    0.07
     찾
    0.07
     should
    0.06
     incorrectly
    0.06
     solving
    0.06
    Activations Density 0.043%

    No Known Activations