© 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. 120248
    Prev
    Next
    INDEX
    Explanations

    school and grades

    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
     pupils
    -0.09
     খি
    -0.07
     youngsters
    -0.07
     pupil
    -0.07
     Pupils
    -0.07
    rianças
    -0.07
     Teacher
    -0.06
     GIRL
    -0.06
     CHILD
    -0.06
     ребят
    -0.06
    POSITIVE LOGITS
     prvi
    0.06
     parte
    0.06
     bize
    0.05
     tampilan
    0.05
     необходимости
    0.05
     प्रस्तु
    0.05
    nę
    0.05
    feedback
    0.05
     первых
    0.05
    first
    0.05
    Activations Density 0.015%

    No Known Activations