© 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. 118152
    Prev
    Next
    INDEX
    Explanations

    mathematical word problems

    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
     somewhat
    -0.07
     prevents
    -0.07
     fairly
    -0.07
     derives
    -0.07
     significantly
    -0.07
     allows
    -0.06
     provides
    -0.06
     suggests
    -0.06
    provides
    -0.06
     カラ
    -0.06
    POSITIVE LOGITS
    André
    0.06
    𝟮
    0.06
    hanam
    0.06
     Schrödinger
    0.06
     každý
    0.06
     अल्को
    0.06
    炰
    0.06
     más
    0.06
     all
    0.06
    jacoco
    0.06
    Activations Density 0.002%

    No Known Activations