© 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. 119312
    Prev
    Next
    INDEX
    Explanations

    names and initials

    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
    今まで
    -0.07
     Certified
    -0.07
    懦
    -0.06
     Martinez
    -0.06
     ostr
    -0.06
     എല്ലാവ
    -0.06
     அவரின்
    -0.06
     altijd
    -0.06
     często
    -0.06
     আস্তে
    -0.06
    POSITIVE LOGITS
     cuya
    0.07
     manufacturers
    0.06
     whose
    0.06
     ún
    0.06
    前半
    0.06
     fabricantes
    0.06
     cuja
    0.06
    ;
    0.05
     பொருத்த
    0.05
     hiçbir
    0.05
    Activations Density 0.053%

    No Known Activations