© 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. 119809
    Prev
    Next
    INDEX
    Explanations

    specific examples or explanations

    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
     மட்டுமே
    -0.07
     இவற்றை
    -0.06
     केवल
    -0.06
    inducing
    -0.06
     manually
    -0.06
    更有
    -0.06
     ب
    -0.05
     दाह
    -0.05
     மல
    -0.05
     solamente
    -0.05
    POSITIVE LOGITS
    ispielsweise
    0.07
     this
    0.07
     esimerkiksi
    0.07
     misalnya
    0.06
    7
    0.06
    ্শন
    0.06
    例えば
    0.06
     each
    0.06
    ->
    0.06
     например
    0.06
    Activations Density 0.125%

    No Known Activations