© 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. 128541
    Prev
    Next
    INDEX
    Explanations

    **beginning of technical or formal phrases**

    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
     subsidiaries
    -0.06
     clock
    -0.06
     INSTIT
    -0.06
     galore
    -0.06
     DIRECT
    -0.06
    全部
    -0.06
     एप्प
    -0.06
     crunchy
    -0.06
    ខ្ញុំ
    -0.06
     moistur
    -0.06
    POSITIVE LOGITS
     misma
    0.07
     insuffisamment
    0.06
     టీ
    0.06
     retain
    0.06
     impromptu
    0.06
    hostname
    0.06
     Acting
    0.05
     jiné
    0.05
     médic
    0.05
    Suzuki
    0.05
    Activations Density 0.001%

    No Known Activations