© 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. 117789
    Prev
    Next
    INDEX
    Explanations

    theoretical framework

    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
    andidates
    -0.06
    ইসলাম
    -0.06
     جميع
    -0.06
     nonsense
    -0.06
     அனைத்து
    -0.06
     illusion
    -0.06
     stb
    -0.06
     neurons
    -0.06
     всеми
    -0.06
     один
    -0.06
    POSITIVE LOGITS
     thrived
    0.06
     брать
    0.06
     specificity
    0.06
     specific
    0.06
     específico
    0.06
     rarity
    0.06
     destac
    0.06
     específicos
    0.06
    specific
    0.06
    沺
    0.06
    Activations Density 0.030%

    No Known Activations