© 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. 119624
    Prev
    Next
    INDEX
    Explanations

    clicking ' or " before commands

    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
     tampoco
    -0.06
     большой
    -0.06
     نموذج
    -0.06
    هام
    -0.06
     মধ্যেও
    -0.06
    ด้วย
    -0.06
     durch
    -0.06
    假的
    -0.06
    nThe
    -0.06
     przez
    -0.06
    POSITIVE LOGITS
     it
    0.07
     they
    0.06
     as
    0.06
     प्रयोग
    0.05
     I
    0.05
     Cllr
    0.05
     there
    0.05
    တတ်
    0.05
     ঘটনা
    0.05
     lesser
    0.05
    Activations Density 0.015%

    No Known Activations