© 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. 117714
    Prev
    Next
    INDEX
    Explanations

    charges and legal violations

    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
     عندما
    -0.07
     Když
    -0.07
     اذا
    -0.07
     Gdy
    -0.07
    如果
    -0.07
     ಯಾರ
    -0.07
     when
    -0.07
     अगर
    -0.07
    If
    -0.07
    When
    -0.07
    POSITIVE LOGITS
     ohne
    0.07
     tôi
    0.07
     without
    0.06
    ire
    0.06
     fără
    0.06
     χωρίς
    0.06
     absolute
    0.06
     ireo
    0.06
     accepted
    0.06
    absolute
    0.06
    Activations Density 0.004%

    No Known Activations