© 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. 128192
    Prev
    Next
    INDEX
    Explanations

    Charles Mann

    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
     structuring
    -0.06
     personne
    -0.06
     necessary
    -0.06
     چین
    -0.06
     استقبال
    -0.06
    ทะ
    -0.05
     """
    -0.05
     quelqu
    -0.05
     ве
    -0.05
     favorable
    -0.05
    POSITIVE LOGITS
    停留
    0.06
    不可以
    0.06
     dibawah
    0.06
    awsze
    0.06
     declared
    0.06
     krank
    0.06
     sécrétion
    0.06
    }-(
    0.06
    주일
    0.06
     audiovis
    0.06
    Activations Density 0.001%

    No Known Activations