© 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. 117146
    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
     như
    -0.07
     hardworking
    -0.06
     Unexpected
    -0.06
     Sections
    -0.06
     invigorating
    -0.06
    様な
    -0.06
     Tong
    -0.06
    Tong
    -0.06
     whiche
    -0.06
    部は
    -0.06
    POSITIVE LOGITS
    或者
    0.07
     not
    0.07
     अथवा
    0.06
     Z
    0.06
     seeking
    0.06
     ještě
    0.06
    enemy
    0.06
     یا
    0.06
     z
    0.05
     ወይም
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.