© 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. 119545
    Prev
    Next
    INDEX
    Explanations

    dates and releases

    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
     bụi
    -0.06
     الدم
    -0.06
     oldest
    -0.06
     deriv
    -0.06
     Dice
    -0.06
     मिन
    -0.06
     míst
    -0.06
    Dice
    -0.06
     Hill
    -0.06
     Dodge
    -0.06
    POSITIVE LOGITS
     stunning
    0.07
     walang
    0.07
     annual
    0.07
    quantum
    0.06
     elegantly
    0.06
     receiving
    0.06
     support
    0.06
     financial
    0.06
     outdoor
    0.06
     trademark
    0.06
    Activations Density 0.009%

    No Known Activations