© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 119136
    Prev
    Next
    INDEX
    Explanations

    CDP, unincorporated communities, parishes

    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
     젊
    -0.06
     şark
    -0.06
     maak
    -0.06
     referred
    -0.06
    ﾋ
    -0.06
     ə
    -0.06
    พื้น
    -0.06
     スト
    -0.05
     ullamco
    -0.05
    <0xE1>
    -0.05
    POSITIVE LOGITS
     ряда
    0.07
    ලය
    0.06
     সিরিজ
    0.06
     burgeoning
    0.06
    ാത്ത
    0.06
     এমন
    0.06
    ltre
    0.06
    collider
    0.06
    もちろん
    0.06
     ряд
    0.06
    Activations Density 0.013%

    No Known Activations