© 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. 119712
    Prev
    Next
    INDEX
    Explanations

    two or three

    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
    <0xE3>
    -0.06
    现在的
    -0.06
    后面
    -0.06
    ové
    -0.06
    কেশন
    -0.06
    这一次
    -0.05
    枴
    -0.05
    后面的
    -0.05
     защиты
    -0.05
     Kram
    -0.05
    POSITIVE LOGITS
     двух
    0.07
     is
    0.07
    只需
    0.06
    itôt
    0.06
     resolute
    0.06
     និង
    0.06
     from
    0.06
     the
    0.06
     three
    0.06
     grandiose
    0.06
    Activations Density 0.001%

    No Known Activations