© 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. 116639
    Prev
    Next
    INDEX
    Explanations

    punctuations and numbers

    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
     throat
    -0.07
    ➳
    -0.06
    考えて
    -0.06
    然后
    -0.06
     values
    -0.06
    ologist
    -0.06
    aggy
    -0.06
     strategies
    -0.06
     then
    -0.06
     Qe
    -0.06
    POSITIVE LOGITS
     Ruskin
    0.06
    apak
    0.06
     оттен
    0.06
     znak
    0.06
    ទេ
    0.05
     প্রতিটি
    0.05
    Each
    0.05
     tiap
    0.05
    the
    0.05
     chút
    0.05
    Activations Density 0.002%

    No Known Activations