© 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. 119395
    Prev
    Next
    INDEX
    Explanations

    InfluxDB line protocol

    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
     নাকের
    -0.07
     entrances
    -0.07
     gory
    -0.06
     Lexus
    -0.06
    福祉
    -0.06
     bmw
    -0.06
     movable
    -0.06
     detachable
    -0.06
     casino
    -0.06
     помощью
    -0.06
    POSITIVE LOGITS
    muy
    0.06
     spécialiste
    0.06
     conservation
    0.06
     容量
    0.06
    බන්ධ
    0.06
    MEL
    0.05
    conservation
    0.05
     wod
    0.05
     overburden
    0.05
     relembrar
    0.05
    Activations Density 0.010%

    No Known Activations