© 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. 118317
    Prev
    Next
    INDEX
    Explanations

    assaults and murders

    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
     ერთი
    -0.08
     một
    -0.06
     смерть
    -0.06
    ίνουν
    -0.06
     absolutamente
    -0.06
     внешней
    -0.06
    మ్యాచ్
    -0.06
     一
    -0.06
    中に
    -0.06
     лаь
    -0.06
    POSITIVE LOGITS
     স্বাস্থ্য
    0.08
     மருத்துவ
    0.07
    醫
    0.07
     safety
    0.07
     medical
    0.07
     neuro
    0.06
    医疗
    0.06
     Medical
    0.06
     Health
    0.06
     медицин
    0.06
    Activations Density 0.002%

    No Known Activations