© 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. 128365
    Prev
    Next
    INDEX
    Explanations

    url path segments

    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
     একমাত্র
    -0.07
     หรือ
    -0.07
     භාවිතා
    -0.06
     பாதிக்கிறது
    -0.06
     hasilnya
    -0.06
     देता
    -0.06
     sende
    -0.06
     అన్ని
    -0.06
     jums
    -0.06
     或
    -0.06
    POSITIVE LOGITS
     सेवाएं
    0.06
    awati
    0.06
     अमेजन
    0.06
     ethnicities
    0.06
     supposed
    0.05
     GOD
    0.05
     থেমে
    0.05
     col
    0.05
     тў
    0.05
    اہ
    0.05
    Activations Density 0.002%

    No Known Activations