© 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. 128621
    Prev
    Next
    INDEX
    Explanations

    intractable interference

    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
    使
    -0.06
     todavía
    -0.06
     दाग
    -0.06
    jež
    -0.06
     ancora
    -0.06
     రావ
    -0.06
    sphinx
    -0.06
     necessities
    -0.06
    能够
    -0.06
     gemäß
    -0.05
    POSITIVE LOGITS
     mudança
    0.06
    ousands
    0.06
     onderdeel
    0.06
     MMA
    0.06
     ziy
    0.06
     letra
    0.06
    kem
    0.06
     belki
    0.06
     ändern
    0.06
    olded
    0.06
    Activations Density 0.077%

    No Known Activations