© 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. 130073
    Prev
    Next
    INDEX
    Explanations

    titles and names

    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
    包括
    -0.07
    ↵
    -0.06
     including
    -0.06
    မှု
    -0.06
     you
    -0.06
    相互
    -0.05
    続け
    -0.05
     obdob
    -0.05
     includes
    -0.05
     includ
    -0.05
    POSITIVE LOGITS
     prototypical
    0.07
     reigning
    0.07
    状態で
    0.07
     unsur
    0.07
     రాజ్యం
    0.07
    于
    0.06
     caractéristique
    0.06
     Государ
    0.06
     žen
    0.06
     quintessential
    0.06
    Activations Density 0.008%

    No Known Activations