© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 118630
    Prev
    Next
    INDEX
    Explanations

    marmalade, jelly, food, dehydrators

    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
    éviter
    -0.06
     hôtels
    -0.06
     good
    -0.06
    ั่ว
    -0.06
     použ
    -0.06
     utilisé
    -0.06
    ⇑
    -0.06
     භාවිතා
    -0.05
     used
    -0.05
    électricité
    -0.05
    POSITIVE LOGITS
     பெண்க
    0.07
     winter
    0.07
    ship
    0.06
     Menurut
    0.06
     According
    0.06
     SUMMER
    0.06
     JULY
    0.06
     offering
    0.06
     autumn
    0.06
    勋
    0.06
    Activations Density 0.007%

    No Known Activations