© 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. 129360
    Prev
    Next
    INDEX
    Explanations

    special characters

    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
     and
    -0.08
     the
    -0.07
    unable
    -0.07
     અને
    -0.06
     alltid
    -0.06
     essential
    -0.06
     eigenen
    -0.06
    +,
    -0.06
     සහ
    -0.06
     okay
    -0.06
    POSITIVE LOGITS
     இயக்க
    0.06
    遭
    0.06
     看
    0.06
     アイ
    0.06
     出
    0.06
     お
    0.05
     church
    0.05
     マ
    0.05
     साथ
    0.05
     শ্রবণ
    0.05
    Activations Density 0.015%

    No Known Activations