© 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. 129407
    Prev
    Next
    INDEX
    Explanations

    specific words or punctuation

    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
     relentless
    -0.06
    owitz
    -0.06
     अर्थात्
    -0.06
    cfg
    -0.06
     Така
    -0.06
     tireless
    -0.06
     CAG
    -0.05
    ফুদ্দিন
    -0.05
     judgmental
    -0.05
     furo
    -0.05
    POSITIVE LOGITS
     inversa
    0.07
     নামটি
    0.06
    ↵
    0.06
    Specific
    0.06
    igna
    0.06
    without
    0.06
    Town
    0.06
    ION
    0.06
    Held
    0.06
    㪯
    0.06
    Activations Density 0.001%

    No Known Activations