© 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. 119776
    Prev
    Next
    INDEX
    Explanations

    specific word or punctuation start

    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
    አ
    -0.06
    jaman
    -0.06
     diamant
    -0.06
    crit
    -0.05
    (${
    -0.05
     പഞ്ച
    -0.05
     enfant
    -0.05
     indestructible
    -0.05
     ১৫
    -0.05
     molé
    -0.05
    POSITIVE LOGITS
     possibly
    0.07
    그리고
    0.07
    Swing
    0.07
    可能是
    0.06
     Swing
    0.06
    evoluzione
    0.06
    하지
    0.06
     bietet
    0.06
     Couple
    0.06
     Scroll
    0.06
    Activations Density 0.007%

    No Known Activations