© 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. 129742
    Prev
    Next
    INDEX
    Explanations

    station or platform descriptions

    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
     abnormally
    -0.06
     anormal
    -0.06
     greatly
    -0.06
    異常
    -0.06
     reasonably
    -0.06
     naturally
    -0.05
     naturalmente
    -0.05
     high
    -0.05
     întâ
    -0.05
     inversely
    -0.05
    POSITIVE LOGITS
    社會
    0.07
    씻
    0.07
     미래
    0.06
     будущее
    0.06
     christian
    0.06
     political
    0.06
     usos
    0.06
    chris
    0.06
     फायदे
    0.06
    offs
    0.06
    Activations Density 0.006%

    No Known Activations