© 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. 116614
    Prev
    Next
    INDEX
    Explanations

    track count or refer

    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
    再一次
    -0.07
     only
    -0.07
    Does
    -0.06
    Only
    -0.06
     does
    -0.06
     neve
    -0.06
     إلا
    -0.06
    望着
    -0.06
    anthe
    -0.05
    Less
    -0.05
    POSITIVE LOGITS
     sirven
    0.07
     FOREIGN
    0.06
    浏
    0.06
     scont
    0.06
     பகுதிக
    0.06
    厠
    0.06
    код
    0.05
     discrete
    0.05
    CITY
    0.05
    以便
    0.05
    Activations Density 0.002%

    No Known Activations