© 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. 116530
    Prev
    Next
    INDEX
    Explanations

    license terms

    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
     непосредственно
    -0.08
     directly
    -0.08
     कुछ
    -0.08
     specifically
    -0.07
     contribute
    -0.07
     регулярно
    -0.07
     یکی
    -0.07
     específicamente
    -0.07
     சர்வதேச
    -0.07
    峣
    -0.07
    POSITIVE LOGITS
    often
    0.07
     adanya
    0.06
    往往
    0.06
    !
    0.06
     suele
    0.06
    whereas
    0.06
     often
    0.06
     जिल्ह्यातील
    0.06
    IL
    0.06
     பண்ண
    0.05
    Activations Density 0.002%

    No Known Activations