© 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. 120278
    Prev
    Next
    INDEX
    Explanations

    start of new sentence or heading

    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
     boyunca
    -0.08
     both
    -0.07
     already
    -0.07
    を通して
    -0.06
     എന്നിവ
    -0.06
     dvě
    -0.06
     실제로
    -0.06
     EVERY
    -0.06
     ஆகியோர்
    -0.06
     BOTH
    -0.06
    POSITIVE LOGITS
     для
    0.06
    会被
    0.06
     Про
    0.06
    書類
    0.06
     uj
    0.06
    ，
    0.06
     domicile
    0.06
    自
    0.06
     
    0.06
     kendi
    0.06
    Activations Density 0.001%

    No Known Activations